diff --git a/src_code_for_reproducibility/docs/source/conf.py b/src_code_for_reproducibility/docs/source/conf.py new file mode 100644 index 0000000000000000000000000000000000000000..5c7512678928b6b7580c812cd62d1c22df9945ba --- /dev/null +++ b/src_code_for_reproducibility/docs/source/conf.py @@ -0,0 +1,48 @@ +# Configuration file for the Sphinx documentation builder. +import os +import sys +sys.path.insert(0, os.path.abspath('../..')) + +# -- Project information ----------------------------------------------------- +project = 'llm_negotiation' +copyright = '2023, Your Name' +author = 'Your Name' + +# -- General configuration --------------------------------------------------- +extensions = [ + 'sphinx.ext.autodoc', + 'sphinx.ext.viewcode', + 'sphinx.ext.napoleon', + 'sphinx.ext.autosummary', + 'sphinx.ext.intersphinx', + 'sphinx.ext.mathjax', + 'sphinxcontrib.mermaid', + 'sphinx_rtd_theme', +] + +templates_path = ['_templates'] +exclude_patterns = [] + +# -- Options for HTML output ------------------------------------------------- +html_theme = 'sphinx_rtd_theme' +html_static_path = ['_static'] + +# -- Napoleon settings ------------------------------------------------------- +napoleon_google_docstring = True +napoleon_numpy_docstring = False +napoleon_include_init_with_doc = True +napoleon_include_private_with_doc = False +napoleon_include_special_with_doc = True +napoleon_use_admonition_for_examples = False +napoleon_use_admonition_for_notes = False +napoleon_use_admonition_for_references = False +napoleon_use_ivar = False +napoleon_use_param = True +napoleon_use_rtype = True +napoleon_preprocess_types = False +napoleon_type_aliases = None +napoleon_attr_annotations = True + +# -- Path setup -------------------------------------------------------------- +# Make sure the project's modules can be found by Sphinx +sys.path.insert(0, os.path.abspath('../../src')) \ No newline at end of file diff --git a/src_code_for_reproducibility/docs/source/contributing.rst b/src_code_for_reproducibility/docs/source/contributing.rst new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/src_code_for_reproducibility/docs/source/environments.rst b/src_code_for_reproducibility/docs/source/environments.rst new file mode 100644 index 0000000000000000000000000000000000000000..fa2fc4fbe9c68edfb5b1726a19a0bdf133c3f879 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/environments.rst @@ -0,0 +1,35 @@ +================= +MARL Environments +================= + +This section provides detailed documentation for the multi-agent negotiation environments included in the library. + +Each environment follows the standard interface described in :doc:`../environments` but has its own unique game rules, +dynamics, and implementation details. + +.. toctree:: + :maxdepth: 2 + :caption: Available Environments: + + environments/ipd + environments/diplomacy + environments/dond + +Overview +-------- + +The library currently includes the following environments: + +1. **Iterated Prisoner's Dilemma (IPD)**: A classic game theory problem where two agents repeatedly decide whether to cooperate or defect, with different payoffs based on their joint actions. + +2. **Diplomacy**: An adaptation of the board game Diplomacy, where seven European powers compete for control of supply centers through strategic moves and alliances. + +3. **Deal or No Deal (DOND)**: A negotiation environment based on `the paper Deal or No Deal? End-to-End Learning for Negotiation Dialogues `_ in which agents negotiate over the distribution of a set of prizes. + +Each environment documentation includes: + +- Game rules and background +- Implementation details +- API reference +- Example usage +- Advanced features and customization options \ No newline at end of file diff --git a/src_code_for_reproducibility/docs/source/index.rst b/src_code_for_reproducibility/docs/source/index.rst new file mode 100644 index 0000000000000000000000000000000000000000..cdc1b79539342a9c95ca0cdd9219bce74a7b2c8a --- /dev/null +++ b/src_code_for_reproducibility/docs/source/index.rst @@ -0,0 +1,22 @@ +Welcome to LLM Negotiation's documentation! +=========================================== +This library is a collection of tools for training and evaluating LLM-based agents in multi-agent environments. It is designed to be easy to use and extend. + +.. toctree:: + :maxdepth: 3 + :caption: Contents: + + installation + marl_standard + environments + launch + usage + modules + contributing + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` \ No newline at end of file diff --git a/src_code_for_reproducibility/docs/source/installation.rst b/src_code_for_reproducibility/docs/source/installation.rst new file mode 100644 index 0000000000000000000000000000000000000000..b148f25d92fd8308e9695f7c17c2b91fb0c9a2c6 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/installation.rst @@ -0,0 +1,10 @@ +Installation +=========== + +To install the package, run: + +.. code-block:: bash + + git clone https://github.com/yourusername/llm_negotiation.git + cd llm_negotiation + pip install -e . \ No newline at end of file diff --git a/src_code_for_reproducibility/docs/source/marl_standard.rst b/src_code_for_reproducibility/docs/source/marl_standard.rst new file mode 100644 index 0000000000000000000000000000000000000000..b5ea5529892c611b34255645ec68537a236754cf --- /dev/null +++ b/src_code_for_reproducibility/docs/source/marl_standard.rst @@ -0,0 +1,141 @@ +================= +Abstract Standard for Multi-Agent Negotiation Environments +================= + +Multi-Agent Negotiation Environments require more features than gymnasium environments in order to be used as interfaces in general game running code. +The two fundamental differences between gymnasium environments and Multi-Agent Negotiation Environments are: + +1. Response from the LLM is a text action, not a discrete action. Therefore, appropriate parsing of the text is required. The model may need to be run multiple times to get the full action. + This is why we introduce the `AgentHandler` class, which is responsible for parsing the LLM's response. +2. The environment needs to be able to handle multi-agent interactions. + This is why we introduce the `NegotiationEnvironment` class, which is responsible for handling the multi-agent interactions. +3. MARL environments are complex to describe. In different contexts, the same environment may be described differently. Therefore, both the environement and the agent handlers are + responsible for describing a particular trajectory. This information is given by the `get_log_info` method. +4. There might be a lot of overlap between the neural networks used by each agent. For instance, the same model may be used for all agents. This motivates a requirement for a + policy identifier for each agent. + +Taking inspiration from the `gymnasium `_ library, we introduce a new standard for Multi-Agent Negotiation Environments. + +Our standard is based on the following features: + +Environments are of the form: + +.. code-block:: python + + class MarlEnvironment(): + + def __init__(self): + """Initialize the environment.""" + pass + + def reset(self): + """Reset the environment to an initial state and return the initial observation. + Returns: + observation (dict): A dictionary where keys are agent identifiers and values are observations. + """ + # (...) + return observation + + def step(self, actions): + """Take a step in the environment using the provided actions. + + Args: + actions (dict): A dictionary where keys are agent identifiers and values are actions. + + Returns: + observations (dict): A dictionary where keys are agent identifiers and values are observations. + reward (dict): A dictionary where keys are agent identifiers and values are rewards. + done (bool): Whether the episode has ended. + info (dict): Additional information about the environment. + """ + # (...) + return observations, done, info + + def get_log_info(self): + """Get additional information about the environment. This information is used to log the game. + Returns: + log_info (dict): Information about the environment required to log the game. + """ + # (...) + return log_info + + def render(self): + """Render the current state of the environment.""" + pass + + def close(self): + """Perform any necessary cleanup.""" + pass + + + class AgentState(): + + def __init__(self): + """Initialize the agent state.""" + pass + + def step(self, observation_from_env, policy_output=None): + """Update the agent state based on the observation and action. + The action is the output of the LLM. + """ + + Args: + observation_from_env (dict): The observation of the environment. + policy_output : The output of the policy. + + Returns: + policy_id (str): The policy identifier. + policy_input (dict): The input to the policy. + action : The official action to be sent to the environment. + done (bool): Whether the LLM action is ready to be sent to the environment. + info (dict): Additional information about the agent. + """ + # (...) + return policy_id, policy_input, action, done, info + + def get_log_info(self): + """Get information about the agent required to log a trajectory. + Returns: + log_info (dict): Information about the agent required to log a trajectory. + """ + # (...) + return log_info + + def render(self): + """Render the current state of the environment.""" + pass + + def close(self): + """Perform any necessary cleanup.""" + pass + + +Implicitely, the keys of the `observations` in the `step` method of the `MarlEnvironment` interface represent the set of agents from which an action is expected at the current step. The next step should only expect actions from the agents in the `observations` dictionary. + +As you can see, both classes have a `get_log_info` method. This method is used to log the game. It returns a dictionary with keys being the agent identifiers and values being the information to log. The reason we need this is because the environment and the agent handler may need to log different information. It makes it easier to log from the perspective of each agent. The core environment class should not need to know about the details of the agent handler. + + + +Running Environments in Parallel +-------------------------------- +This standard allows the use of the `run_batched_matches` function (TODO: link) to run environments in an efficient way. The core idea is to batch the policy calls for all agents in the environment. + +.. note:: + The ``run_batched_matches`` function allows you to run multiple negotiation games, or "matches," in parallel. + After each environment is initialized, the function continuously loops over all active matches and checks which agents + are still pending actions. Each agent's logic can require multiple calls to the policy (e.g., an LLM) before an action + becomes "ready" to be sent to the environment. (For instance, an agent might need multiple policy calls before having a string which can be parsed into a valid action.) While an agent is waiting for a policy output, these calls for all agents across all matches are grouped together by unique policy identifier and processed in batch for efficiency. This is the core functionality of the ``run_batched_matches`` function. + + Only once all actions from the required agents at a given step for an environment are ready does the function make a single ``env.step(...)`` call; this ensures + every match moves forward in lockstep for all its active agents. As soon as an environment signals it is done, the function + retrieves logged information from both the environment and the agent states before removing this match from the active set. + + If there are more matches waiting to be processed, they are then started one by one to maintain the specified degree of parallelism. + This batching approach provides an efficient mechanism to handle multi-agent or multi-policy environments, ensuring minimal + overhead and a clear, unified flow for stepping through matches. + +Here is a diagram that shows how the `run_batched_matches` function works at a high level: + +.. image:: media/runbatch.png + :alt: Alternate text for the image + :width: 1000px diff --git a/src_code_for_reproducibility/docs/source/modules.rst b/src_code_for_reproducibility/docs/source/modules.rst new file mode 100644 index 0000000000000000000000000000000000000000..e9ff8ac1a89c7bd18e69d633121f5a4022ac6fdf --- /dev/null +++ b/src_code_for_reproducibility/docs/source/modules.rst @@ -0,0 +1,7 @@ +src +=== + +.. toctree:: + :maxdepth: 4 + + src diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.dond_agent.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_agent.rst new file mode 100644 index 0000000000000000000000000000000000000000..8fab765a9c7e749bd446533fdddb5fa5b55e6635 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_agent.rst @@ -0,0 +1,7 @@ +src.environments.dond.dond\_agent module +======================================== + +.. automodule:: src.environments.dond.dond_agent + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.dond_game.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_game.rst new file mode 100644 index 0000000000000000000000000000000000000000..d0e595aad169a5a8456f83afe5029e7475d7c9e7 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_game.rst @@ -0,0 +1,7 @@ +src.environments.dond.dond\_game module +======================================= + +.. automodule:: src.environments.dond.dond_game + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.dond_log_funcs.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_log_funcs.rst new file mode 100644 index 0000000000000000000000000000000000000000..cf96327d1bcbc7f0f8785804a49a6975eef889c2 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_log_funcs.rst @@ -0,0 +1,7 @@ +src.environments.dond.dond\_log\_funcs module +============================================= + +.. automodule:: src.environments.dond.dond_log_funcs + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.dond_player.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_player.rst new file mode 100644 index 0000000000000000000000000000000000000000..bab97f1009eb2d5c4e387ac6a83982a51e33c9e3 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_player.rst @@ -0,0 +1,7 @@ +src.environments.dond.dond\_agent module +========================================= + +.. automodule:: src.environments.dond.dond_agent + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.dond_return_funcs.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_return_funcs.rst new file mode 100644 index 0000000000000000000000000000000000000000..e8084f8f9a291efe75e032183ebd5eeab58f5e41 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_return_funcs.rst @@ -0,0 +1,7 @@ +src.environments.dond.dond\_return\_funcs module +================================================ + +.. automodule:: src.environments.dond.dond_return_funcs + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.dond_statistics_funcs.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_statistics_funcs.rst new file mode 100644 index 0000000000000000000000000000000000000000..4c4d3764f9333b8a2975069160f40952f324a1a8 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_statistics_funcs.rst @@ -0,0 +1,7 @@ +src.environments.dond.dond\_statistics\_funcs module +==================================================== + +.. automodule:: src.environments.dond.dond_statistics_funcs + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.dond_training_data_funcs.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_training_data_funcs.rst new file mode 100644 index 0000000000000000000000000000000000000000..cf31d696a3ed580e24f3c5dffd6f7a2851d16320 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.dond_training_data_funcs.rst @@ -0,0 +1,7 @@ +src.environments.dond.dond\_training\_data\_funcs module +======================================================== + +.. automodule:: src.environments.dond.dond_training_data_funcs + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.dond.rst b/src_code_for_reproducibility/docs/source/src.environments.dond.rst new file mode 100644 index 0000000000000000000000000000000000000000..8462de2bdb96d31b5628cfd2942131e13e4e9dc3 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.dond.rst @@ -0,0 +1,19 @@ +src.environments.dond package +============================= + +.. automodule:: src.environments.dond + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.environments.dond.dond_agent + src.environments.dond.dond_game + src.environments.dond.dond_log_funcs + src.environments.dond.dond_statistics_funcs + src.environments.dond.dond_training_data_funcs diff --git a/src_code_for_reproducibility/docs/source/src.environments.env_imports.rst b/src_code_for_reproducibility/docs/source/src.environments.env_imports.rst new file mode 100644 index 0000000000000000000000000000000000000000..4354ba27eee9f0e0fa3f4f0e5d9131c256a4be57 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.env_imports.rst @@ -0,0 +1,7 @@ +src.environments.env\_imports module +==================================== + +.. automodule:: src.environments.env_imports + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.environment_imports.rst b/src_code_for_reproducibility/docs/source/src.environments.environment_imports.rst new file mode 100644 index 0000000000000000000000000000000000000000..d22c53e31cd1c7c064955900c19f34ac51c7006f --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.environment_imports.rst @@ -0,0 +1,7 @@ +src.environments.environment\_imports module +============================================ + +.. automodule:: src.environments.environment_imports + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_agent.rst b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_agent.rst new file mode 100644 index 0000000000000000000000000000000000000000..4845b371089c529493f70de77ceaee0b7500571b --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_agent.rst @@ -0,0 +1,7 @@ +src.environments.ipd.ipd\_agent module +====================================== + +.. automodule:: src.environments.ipd.ipd_agent + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_game.rst b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_game.rst new file mode 100644 index 0000000000000000000000000000000000000000..ede471ef9675c780410189fcf63df0c1a05496d0 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_game.rst @@ -0,0 +1,7 @@ +src.environments.ipd.ipd\_game module +===================================== + +.. automodule:: src.environments.ipd.ipd_game + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_log_funcs.rst b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_log_funcs.rst new file mode 100644 index 0000000000000000000000000000000000000000..edec187f4876cdf653ae4f91035f43bc877a7d40 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_log_funcs.rst @@ -0,0 +1,7 @@ +src.environments.ipd.ipd\_log\_funcs module +=========================================== + +.. automodule:: src.environments.ipd.ipd_log_funcs + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_statistics_funcs.rst b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_statistics_funcs.rst new file mode 100644 index 0000000000000000000000000000000000000000..5f54afac07c4d477067ef4c2bf5d883b236cf5fc --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_statistics_funcs.rst @@ -0,0 +1,7 @@ +src.environments.ipd.ipd\_statistics\_funcs module +================================================== + +.. automodule:: src.environments.ipd.ipd_statistics_funcs + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_training_data_funcs.rst b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_training_data_funcs.rst new file mode 100644 index 0000000000000000000000000000000000000000..8e4cecea10e25644ff677416823069cd65b500c5 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_training_data_funcs.rst @@ -0,0 +1,7 @@ +src.environments.ipd.ipd\_training\_data\_funcs module +====================================================== + +.. automodule:: src.environments.ipd.ipd_training_data_funcs + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.environments.ipd.rst b/src_code_for_reproducibility/docs/source/src.environments.ipd.rst new file mode 100644 index 0000000000000000000000000000000000000000..af26091b3a87dee4d6993f0ae09bdb1c380a130e --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.ipd.rst @@ -0,0 +1,19 @@ +src.environments.ipd package +============================ + +.. automodule:: src.environments.ipd + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.environments.ipd.ipd_agent + src.environments.ipd.ipd_game + src.environments.ipd.ipd_log_funcs + src.environments.ipd.ipd_statistics_funcs + src.environments.ipd.ipd_training_data_funcs diff --git a/src_code_for_reproducibility/docs/source/src.environments.rst b/src_code_for_reproducibility/docs/source/src.environments.rst new file mode 100644 index 0000000000000000000000000000000000000000..221ed1c07ebea145cd23bc06c6474d34b1d8a33e --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.environments.rst @@ -0,0 +1,25 @@ +src.environments package +======================== + +.. automodule:: src.environments + :members: + :undoc-members: + :show-inheritance: + +Subpackages +----------- + +.. toctree:: + :maxdepth: 4 + + src.environments.dond + src.environments.ipd + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.environments.env_imports + src.environments.environment_imports diff --git a/src_code_for_reproducibility/docs/source/src.experiments.arithmetic_test.rst b/src_code_for_reproducibility/docs/source/src.experiments.arithmetic_test.rst new file mode 100644 index 0000000000000000000000000000000000000000..68e0f5da020aee80cc8895ca650a6067317f4bcd --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.experiments.arithmetic_test.rst @@ -0,0 +1,7 @@ +src.experiments.arithmetic\_test module +======================================= + +.. automodule:: src.experiments.arithmetic_test + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.experiments.dond_run_train.rst b/src_code_for_reproducibility/docs/source/src.experiments.dond_run_train.rst new file mode 100644 index 0000000000000000000000000000000000000000..6c94e4bc508836338d5d6393858d403e746b5d2d --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.experiments.dond_run_train.rst @@ -0,0 +1,7 @@ +src.experiments.dond\_run\_train module +======================================= + +.. automodule:: src.experiments.dond_run_train + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.experiments.generate_and_train.rst b/src_code_for_reproducibility/docs/source/src.experiments.generate_and_train.rst new file mode 100644 index 0000000000000000000000000000000000000000..d0d0a0ccdf7839f6c192107d1ad91af4aaadda7b --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.experiments.generate_and_train.rst @@ -0,0 +1,7 @@ +src.experiments.generate\_and\_train module +=========================================== + +.. automodule:: src.experiments.generate_and_train + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.experiments.last_completion.rst b/src_code_for_reproducibility/docs/source/src.experiments.last_completion.rst new file mode 100644 index 0000000000000000000000000000000000000000..1b868ee566283d662a51387046bc070a131f5222 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.experiments.last_completion.rst @@ -0,0 +1,7 @@ +src.experiments.last\_completion module +======================================= + +.. automodule:: src.experiments.last_completion + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.experiments.rst b/src_code_for_reproducibility/docs/source/src.experiments.rst new file mode 100644 index 0000000000000000000000000000000000000000..90f61ff53afa0281b9e6b82188eb2df30b81eb07 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.experiments.rst @@ -0,0 +1,17 @@ +src.experiments package +======================= + +.. automodule:: src.experiments + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.experiments.arithmetic_test + src.experiments.generate_and_train + src.experiments.last_completion diff --git a/src_code_for_reproducibility/docs/source/src.generation.rst b/src_code_for_reproducibility/docs/source/src.generation.rst new file mode 100644 index 0000000000000000000000000000000000000000..14bb2b1364da7067aed5c37e3c77d091d20f011b --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.generation.rst @@ -0,0 +1,15 @@ +src.generation package +====================== + +.. automodule:: src.generation + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.generation.run_games diff --git a/src_code_for_reproducibility/docs/source/src.generation.run_games.rst b/src_code_for_reproducibility/docs/source/src.generation.run_games.rst new file mode 100644 index 0000000000000000000000000000000000000000..dbf42d3f821df187cdd4a8bb9d093839ce6b608a --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.generation.run_games.rst @@ -0,0 +1,7 @@ +src.generation.run\_games module +================================ + +.. automodule:: src.generation.run_games + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.dummy_hf_agent.rst b/src_code_for_reproducibility/docs/source/src.models.dummy_hf_agent.rst new file mode 100644 index 0000000000000000000000000000000000000000..937900b392b98e7f01968d496ae0c350a836d632 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.dummy_hf_agent.rst @@ -0,0 +1,7 @@ +src.models.dummy\_hf\_agent module +================================== + +.. automodule:: src.models.dummy_llm_agent + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.dummy_local_llm.rst b/src_code_for_reproducibility/docs/source/src.models.dummy_local_llm.rst new file mode 100644 index 0000000000000000000000000000000000000000..13b40bd388e445fa60a3c3fc2e089ad89c452dbd --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.dummy_local_llm.rst @@ -0,0 +1,7 @@ +src.models.dummy\_local\_llm module +=================================== + +.. automodule:: src.models.dummy_local_llm + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.hf_agent.rst b/src_code_for_reproducibility/docs/source/src.models.hf_agent.rst new file mode 100644 index 0000000000000000000000000000000000000000..e96abf4e21b1523cd016c6172eed0ddf51b4954a --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.hf_agent.rst @@ -0,0 +1,7 @@ +src.models.hf\_agent module +=========================== + +.. automodule:: src.models.hf_agent + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.local_llm.rst b/src_code_for_reproducibility/docs/source/src.models.local_llm.rst new file mode 100644 index 0000000000000000000000000000000000000000..5c2eebb05e64919d1915eeb63dc18f5e9a36eb2c --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.local_llm.rst @@ -0,0 +1,7 @@ +src.models.local\_llm module +============================ + +.. automodule:: src.models.local_llm + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.new_local_llm.rst b/src_code_for_reproducibility/docs/source/src.models.new_local_llm.rst new file mode 100644 index 0000000000000000000000000000000000000000..d65981b7a6bbf99327fb467a63644bbe98d137f4 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.new_local_llm.rst @@ -0,0 +1,7 @@ +src.models.new\_local\_llm module +================================= + +.. automodule:: src.models.new_local_llm + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.oai_agent.rst b/src_code_for_reproducibility/docs/source/src.models.oai_agent.rst new file mode 100644 index 0000000000000000000000000000000000000000..bd7da8bb6cfc8426bd9725b0ccaf58cfe91eee93 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.oai_agent.rst @@ -0,0 +1,7 @@ +src.models.oai\_agent module +============================ + +.. automodule:: src.models.oai_agent + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.rst b/src_code_for_reproducibility/docs/source/src.models.rst new file mode 100644 index 0000000000000000000000000000000000000000..d03983340a5b0317354d1895df709277d5a4baed --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.rst @@ -0,0 +1,20 @@ +src.models package +================== + +.. automodule:: src.models + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.models.dummy_local_llm + src.models.local_llm + src.models.new_local_llm + src.models.server_llm + src.models.updatable_worker + src.models.vllm_worker_wrap diff --git a/src_code_for_reproducibility/docs/source/src.models.server_llm.rst b/src_code_for_reproducibility/docs/source/src.models.server_llm.rst new file mode 100644 index 0000000000000000000000000000000000000000..6b832a40dafe00b5e56b4060dc07e4dda0a03bad --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.server_llm.rst @@ -0,0 +1,7 @@ +src.models.server\_llm module +============================= + +.. automodule:: src.models.server_llm + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.updatable_worker.rst b/src_code_for_reproducibility/docs/source/src.models.updatable_worker.rst new file mode 100644 index 0000000000000000000000000000000000000000..ee05dfbe7dd407eed4e275f525c04ca6f2c857ae --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.updatable_worker.rst @@ -0,0 +1,7 @@ +src.models.updatable\_worker module +=================================== + +.. automodule:: src.models.updatable_worker + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.models.vllm_worker_wrap.rst b/src_code_for_reproducibility/docs/source/src.models.vllm_worker_wrap.rst new file mode 100644 index 0000000000000000000000000000000000000000..466f755e064534683462b4259876d874678290ed --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.models.vllm_worker_wrap.rst @@ -0,0 +1,7 @@ +src.models.vllm\_worker\_wrap module +==================================== + +.. automodule:: src.models.vllm_worker_wrap + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.rst b/src_code_for_reproducibility/docs/source/src.rst new file mode 100644 index 0000000000000000000000000000000000000000..d2dcff7e18f979e933a27467f4893f3ad5372a88 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.rst @@ -0,0 +1,28 @@ +src package +=========== + +.. automodule:: src + :members: + :undoc-members: + :show-inheritance: + +Subpackages +----------- + +.. toctree:: + :maxdepth: 4 + + src.environments + src.experiments + src.generation + src.models + src.training + src.utils + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.run diff --git a/src_code_for_reproducibility/docs/source/src.run.rst b/src_code_for_reproducibility/docs/source/src.run.rst new file mode 100644 index 0000000000000000000000000000000000000000..379615bab324e654401411db23058b5eec87e277 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.run.rst @@ -0,0 +1,7 @@ +src.run module +============== + +.. automodule:: src.run + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.training.ppo_train.rst b/src_code_for_reproducibility/docs/source/src.training.ppo_train.rst new file mode 100644 index 0000000000000000000000000000000000000000..98f9e085b16ddcfcdecf4237345cb4c1b36b8b80 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.training.ppo_train.rst @@ -0,0 +1,7 @@ +src.training.ppo\_train module +============================== + +.. automodule:: src.training.ppo_train + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.training.ppo_train_value_head.rst b/src_code_for_reproducibility/docs/source/src.training.ppo_train_value_head.rst new file mode 100644 index 0000000000000000000000000000000000000000..a8d6e526eacfce47fac83a7e4617e04db56ecee2 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.training.ppo_train_value_head.rst @@ -0,0 +1,7 @@ +src.training.ppo\_train\_value\_head module +=========================================== + +.. automodule:: src.training.ppo_train_value_head + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.training.reinforce_training.rst b/src_code_for_reproducibility/docs/source/src.training.reinforce_training.rst new file mode 100644 index 0000000000000000000000000000000000000000..5daf4b7250022f523242d6239d0921f362df6d24 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.training.reinforce_training.rst @@ -0,0 +1,7 @@ +src.training.reinforce\_training module +======================================= + +.. automodule:: src.training.reinforce_training + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.training.rl_convs_processing.rst b/src_code_for_reproducibility/docs/source/src.training.rl_convs_processing.rst new file mode 100644 index 0000000000000000000000000000000000000000..cf5db1aa0cb6d010fc70f86c341467ba5e9b485e --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.training.rl_convs_processing.rst @@ -0,0 +1,7 @@ +src.training.rl\_convs\_processing module +========================================= + +.. automodule:: src.training.rl_convs_processing + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.training.rst b/src_code_for_reproducibility/docs/source/src.training.rst new file mode 100644 index 0000000000000000000000000000000000000000..50539fcda2bffa46a72eb48874a7532bf296ff27 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.training.rst @@ -0,0 +1,19 @@ +src.training package +==================== + +.. automodule:: src.training + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.training.ppo_train + src.training.ppo_train_value_head + src.training.reinforce_training + src.training.rl_convs_processing + src.training.train_main diff --git a/src_code_for_reproducibility/docs/source/src.training.train_main.rst b/src_code_for_reproducibility/docs/source/src.training.train_main.rst new file mode 100644 index 0000000000000000000000000000000000000000..838f9ac1cfb2cecd48b2e3d241e7a80c7b86fe25 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.training.train_main.rst @@ -0,0 +1,7 @@ +src.training.train\_main module +=============================== + +.. automodule:: src.training.train_main + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.common_imports.rst b/src_code_for_reproducibility/docs/source/src.utils.common_imports.rst new file mode 100644 index 0000000000000000000000000000000000000000..681ca0651b9298cad189c2b3e7812ba3d31e669f --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.common_imports.rst @@ -0,0 +1,7 @@ +src.utils.common\_imports module +================================ + +.. automodule:: src.utils.common_imports + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.export_ppo_training_set.rst b/src_code_for_reproducibility/docs/source/src.utils.export_ppo_training_set.rst new file mode 100644 index 0000000000000000000000000000000000000000..d05da7df25cb21d8abece3f920c1fb4b88f34d0f --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.export_ppo_training_set.rst @@ -0,0 +1,7 @@ +src.utils.export\_ppo\_training\_set module +=========================================== + +.. automodule:: src.utils.export_ppo_training_set + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.extra_stats.rst b/src_code_for_reproducibility/docs/source/src.utils.extra_stats.rst new file mode 100644 index 0000000000000000000000000000000000000000..7c3e1618d4ae00fc7fc021bf6b96178618321c82 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.extra_stats.rst @@ -0,0 +1,7 @@ +src.utils.extra\_stats module +============================= + +.. automodule:: src.utils.extra_stats + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.inherit_args.rst b/src_code_for_reproducibility/docs/source/src.utils.inherit_args.rst new file mode 100644 index 0000000000000000000000000000000000000000..72d8fc0ff082f4e6d37a852f3dd18a23f58f036d --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.inherit_args.rst @@ -0,0 +1,7 @@ +src.utils.inherit\_args module +============================== + +.. automodule:: src.utils.inherit_args + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.log_statistics.rst b/src_code_for_reproducibility/docs/source/src.utils.log_statistics.rst new file mode 100644 index 0000000000000000000000000000000000000000..fde4c1553a35b932ba59aef8d29ceb90b20df48c --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.log_statistics.rst @@ -0,0 +1,7 @@ +src.utils.log\_statistics module +================================ + +.. automodule:: src.utils.log_statistics + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.model_to_cpu.rst b/src_code_for_reproducibility/docs/source/src.utils.model_to_cpu.rst new file mode 100644 index 0000000000000000000000000000000000000000..e98c6dee2e4eb9bd18ec1cb36d6b00740daffb90 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.model_to_cpu.rst @@ -0,0 +1,7 @@ +src.utils.model\_to\_cpu module +=============================== + +.. automodule:: src.utils.model_to_cpu + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.parallel_shuffle.rst b/src_code_for_reproducibility/docs/source/src.utils.parallel_shuffle.rst new file mode 100644 index 0000000000000000000000000000000000000000..3ea9301dcc1ccb245e1c565a135447348244cd65 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.parallel_shuffle.rst @@ -0,0 +1,7 @@ +src.utils.parallel\_shuffle module +================================== + +.. automodule:: src.utils.parallel_shuffle + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.quick_stats.rst b/src_code_for_reproducibility/docs/source/src.utils.quick_stats.rst new file mode 100644 index 0000000000000000000000000000000000000000..76a504eeda8c9b608e1b331cd932fd2f26bffafb --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.quick_stats.rst @@ -0,0 +1,7 @@ +src.utils.quick\_stats module +============================= + +.. automodule:: src.utils.quick_stats + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/src.utils.rst b/src_code_for_reproducibility/docs/source/src.utils.rst new file mode 100644 index 0000000000000000000000000000000000000000..4f5cb352cc9ec645c968d0ae99798d47c018c750 --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.rst @@ -0,0 +1,24 @@ +src.utils package +================= + +.. automodule:: src.utils + :members: + :undoc-members: + :show-inheritance: + +Submodules +---------- + +.. toctree:: + :maxdepth: 4 + + src.utils.common_imports + src.utils.export_ppo_training_set + src.utils.extra_stats + src.utils.inherit_args + src.utils.log_gpu_usage + src.utils.log_statistics + src.utils.model_to_cpu + src.utils.parallel_shuffle + src.utils.quick_stats + src.utils.update_start_epoch diff --git a/src_code_for_reproducibility/docs/source/src.utils.update_start_epoch.rst b/src_code_for_reproducibility/docs/source/src.utils.update_start_epoch.rst new file mode 100644 index 0000000000000000000000000000000000000000..72cbad9bd09e056213a2e4cd00a6ba624be333cb --- /dev/null +++ b/src_code_for_reproducibility/docs/source/src.utils.update_start_epoch.rst @@ -0,0 +1,7 @@ +src.utils.update\_start\_epoch module +===================================== + +.. automodule:: src.utils.update_start_epoch + :members: + :undoc-members: + :show-inheritance: diff --git a/src_code_for_reproducibility/docs/source/usage.rst b/src_code_for_reproducibility/docs/source/usage.rst new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/src_code_for_reproducibility/markov_games/ipd/__pycache__/Ipd_hard_coded_agents.cpython-312.pyc b/src_code_for_reproducibility/markov_games/ipd/__pycache__/Ipd_hard_coded_agents.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..354fbab18d57425054c5e83b8a8c467d967ddccc Binary files /dev/null and b/src_code_for_reproducibility/markov_games/ipd/__pycache__/Ipd_hard_coded_agents.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/ipd/__pycache__/__init__.cpython-312.pyc b/src_code_for_reproducibility/markov_games/ipd/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2ad972161150c1335d840f5d86f3a662a30f5826 Binary files /dev/null and b/src_code_for_reproducibility/markov_games/ipd/__pycache__/__init__.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_agent.cpython-312.pyc b/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_agent.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e1154ff84f7e1316b3bb49a684c6e5c789276cb1 Binary files /dev/null and b/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_agent.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_simulation.cpython-312.pyc b/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_simulation.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c559efc356f340201bb70a3558c4b9abe6a5c7df Binary files /dev/null and b/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_simulation.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_statistics.cpython-312.pyc b/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_statistics.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0bf55aa8dc1407f9fa71222cef9dd1ef44f6be6d Binary files /dev/null and b/src_code_for_reproducibility/markov_games/ipd/__pycache__/ipd_statistics.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/dond_agent.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/dond_agent.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5c3cdd472992d134e05776b55eeeaea51ef72feb Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/dond_agent.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/dond_simulation.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/dond_simulation.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f30a76c150da8a74c1987b2d712c714b6b3bea49 Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/dond_simulation.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/nego_hard_coded_policies.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/nego_hard_coded_policies.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7d0e8f66077980f9dca7955a12d324c195ff89ce Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/nego_hard_coded_policies.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/no_press_nego_agent.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/no_press_nego_agent.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ad86d92929bd6c38a1aeba2fa3d8ad619cab45df Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/no_press_nego_agent.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/no_press_nego_simulation.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/no_press_nego_simulation.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0c9443951c86d71f7d7150be5007aee9061220f2 Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/no_press_nego_simulation.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_agent.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_agent.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c8c381a73774bad0361fbe12560a32c645ca13dc Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_agent.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_rps_agent.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_rps_agent.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9228dcd110476851547e76bac7ba6f795c991a0a Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_rps_agent.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simple_agent.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simple_agent.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..708db5895faf46b2e0eba53b1fe8567e7b17cde1 Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simple_agent.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simple_simulation.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simple_simulation.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..19528e275e9b4653c58fd3f011cbc819b5351403 Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simple_simulation.cpython-312.pyc differ diff --git a/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simulation.cpython-312.pyc b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simulation.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..67cba7cc63da526ed267724c423a113da94355ea Binary files /dev/null and b/src_code_for_reproducibility/markov_games/negotiation/__pycache__/tas_simulation.cpython-312.pyc differ