Hugging Face's logo

AllIllusion
/
LunarLander-v3

Reinforcement Learning
stable-baselines3
LunarLander-v3
deep-reinforcement-learning
SL-Sprout
Eval Results (legacy)
Model card Files
xet
 Community
AllIllusion commited on
Commit
a3a1d7e
·
verified ·
1 Parent(s): 6e297f9

Upload PPO LunarLander-v3 LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K.zip

Browse files
Files changed (9) hide show
  1. LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K.zip +2 -2
  2. LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/data +23 -23
  3. LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/policy.optimizer.pth +1 -1
  4. LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/policy.pth +1 -1
  5. LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/system_info.txt +1 -0
  6. README.md +1 -1
  7. config.json +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08c57333175d82a72dd89561db9339d6bd95f529880292e576d0d31ade67eca1
3
- size 150637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8767c9d5d83f92edf928aae245ef30e1ea6bb396cbf8e6d89fedac8cb05ae8bb
3
+ size 150650
LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/data CHANGED
@@ -4,20 +4,20 @@
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
- "__init__": "<function ActorCriticPolicy.__init__ at 0x7fccdc1c3d80>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fccdc1c3e20>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fccdc1c3ec0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fccdc1c3f60>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7fccdc1c8040>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7fccdc1c80e0>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fccdc1c8180>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fccdc1c8220>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7fccdc1c82c0>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fccdc1c8360>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fccdc1c8400>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fccdc1c84a0>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7fccdc1c5900>"
21
  },
22
  "verbose": 0,
23
  "policy_kwargs": {},
@@ -26,12 +26,12 @@
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
- "start_time": 1743987234506560551,
30
  "learning_rate": 0.0003,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
- ":serialized:": "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"
35
  },
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
45
  "_stats_window_size": 100,
46
  "ep_info_buffer": {
47
  ":type:": "<class 'collections.deque'>",
48
- ":serialized:": "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"
49
  },
50
  "ep_success_buffer": {
51
  ":type:": "<class 'collections.deque'>",
@@ -89,14 +89,14 @@
89
  "__module__": "stable_baselines3.common.buffers",
90
  "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
91
  "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
92
- "__init__": "<function RolloutBuffer.__init__ at 0x7fccde671f80>",
93
- "reset": "<function RolloutBuffer.reset at 0x7fccde672020>",
94
- "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fccde6720c0>",
95
- "add": "<function RolloutBuffer.add at 0x7fccde672200>",
96
- "get": "<function RolloutBuffer.get at 0x7fccde6722a0>",
97
- "_get_samples": "<function RolloutBuffer._get_samples at 0x7fccde672340>",
98
  "__abstractmethods__": "frozenset()",
99
- "_abc_impl": "<_abc._abc_data object at 0x7fccde667f40>"
100
  },
101
  "rollout_buffer_kwargs": {},
102
  "batch_size": 64,
 
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
+ "__init__": "<function ActorCriticPolicy.__init__ at 0x7f6d6bd92700>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6d6bd927a0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6d6bd92840>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6d6bd928e0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f6d6bd92980>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f6d6bd92a20>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6d6bd92ac0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6d6bd92b60>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f6d6bd92c00>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6d6bd92ca0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6d6bd92d40>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6d6bd92de0>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f6d766fdec0>"
21
  },
22
  "verbose": 0,
23
  "policy_kwargs": {},
 
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1744137563006229533,
30
  "learning_rate": 0.0003,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "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"
35
  },
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
 
45
  "_stats_window_size": 100,
46
  "ep_info_buffer": {
47
  ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "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"
49
  },
50
  "ep_success_buffer": {
51
  ":type:": "<class 'collections.deque'>",
 
89
  "__module__": "stable_baselines3.common.buffers",
90
  "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
91
  "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
92
+ "__init__": "<function RolloutBuffer.__init__ at 0x7f6d6bf502c0>",
93
+ "reset": "<function RolloutBuffer.reset at 0x7f6d6bf50360>",
94
+ "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f6d6bf50400>",
95
+ "add": "<function RolloutBuffer.add at 0x7f6d6bf50540>",
96
+ "get": "<function RolloutBuffer.get at 0x7f6d6bf505e0>",
97
+ "_get_samples": "<function RolloutBuffer._get_samples at 0x7f6d6bf50680>",
98
  "__abstractmethods__": "frozenset()",
99
+ "_abc_impl": "<_abc._abc_data object at 0x7f6d6bf07800>"
100
  },
101
  "rollout_buffer_kwargs": {},
102
  "batch_size": 64,
LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9156d41afe8274854fca2178d4c9605133a57def7c501bc6df2e5c020ffa2aec
3
  size 87978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40c56900986c5e444751384ebbe84be56a3d799b66333ee138ae6417593ddff
3
  size 87978
LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4616786f22ff23690fb53eacc859a421b982ee4b3acdfa517eacde7aca4fa171
3
  size 43634
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99165d15bf03b57f41b06b70073346dfd483adc22010d8fb486695e8c8cc50a6
3
  size 43634
LunarLander-v3_PPO_ne16_ns1024_b64_e4_cpu_TotalStep1000K/system_info.txt CHANGED
@@ -6,3 +6,4 @@
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.1.1
 
 
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.1.1
9
+ - OpenAI Gym: 0.26.2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: LunarLander-v3
17
  metrics:
18
  - type: mean_reward
19
- value: -135.79 +/- 47.54
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: 274.50 +/- 26.72
20
  name: mean_reward
21
  verified: false
22
  ---
config.json CHANGED
@@ -1 +1 @@
1
- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f1945636700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f19456367a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1945636840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f19456368e0>", "_build": "<function ActorCriticPolicy._build at 0x7f1945636980>", "forward": "<function ActorCriticPolicy.forward at 0x7f1945636a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f1945636ac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1945636b60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f1945636c00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1945636ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1945636d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1945636de0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f19455fab40>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 1048576, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1744137552278125891, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFGFgydnTRaMAWyUS1KMAXSUR0CIzmqZtvXLdX2UKGgGR8BXeb0J4SpSaAdLb2gIR0CIzme8PFvRdX2UKGgGR8BLbvGACnxbaAdLSGgIR0CIzlSydFvydX2UKGgGR8BRYmEwnH/+aAdLimgIR0CIzsRsdkrgdX2UKGgGR8BYC7ncL0BfaAdLYGgIR0CIz4IQe3hGdX2UKGgGR8BM55k9U0emaAdLdWgIR0CIzxdonKGMdX2UKGgGR8BCJFGXokiVaAdLPmgIR0CIzxdweeWfdX2UKGgGR8BJg6shgVoIaAdLgGgIR0CIzxcNYr8SdX2UKGgGR8BRGtQ0oBq9aAdLUGgIR0CIz6pbUwztdX2UKGgGR8BSJxnezlcRaAdLe2gIR0CI0JALy+YddX2UKGgGR8BUcf3evZAZaAdLb2gIR0CI0IfjCHh1dX2UKGgGR8BHhO/tY0VKaAdLSmgIR0CI0FBsyi22dX2UKGgGR8BQU3J9y926aAdLP2gIR0CI0DWq94/vdX2UKGgGR8BC+1M/QjUvaAdLZGgIR0CIz9dLQHAzdX2UKGgGR8BXM7gXMyJsaAdLYWgIR0CI0U/7iyY5dX2UKGgGR8BI3aKUFB6baAdLfmgIR0CI0Rr30wrUdX2UKGgGR8BI9b6Hj6vaaAdLfWgIR0CI0G6gdwNtdX2UKGgGR8BYvkt7KJVKaAdLgmgIR0CI0ZtFa0QcdX2UKGgGR8BUN/CZWq95aAdLYmgIR0CI0Uq0dBBzdX2UKGgGR8BI2ssg+yJLaAdLj2gIR0CI0Qa2nbZfdX2UKGgGR8BSAdbLU1AJaAdLTmgIR0CI0QhFmWdFdX2UKGgGR8BGS8AR02cbaAdLXWgIR0CI0eW8AaNudX2UKGgGR8BSheee4Cp4aAdLiWgIR0CI0a/QjUutdX2UKGgGR8BPISwW3z+WaAdLUmgIR0CI0tR/EwWWdX2UKGgGR8BM1k1l5GBnaAdLTGgIR0CI0tXZGrjpdX2UKGgGR8BXgqCYkVvdaAdLc2gIR0CI07m7J4jbdX2UKGgGR8A2BqtHQQcxaAdLemgIR0CI05hZQpF1dX2UKGgGR8BJ92rn1WbPaAdLh2gIR0CI1XBZ6lchdX2UKGgGR8A5aVsUIsy0aAdLZ2gIR0CI1UA5Jbt7dX2UKGgGR8BHFwl8gIQfaAdLVGgIR0CI1PUBGQS0dX2UKGgGR8BNXMH8jzI4aAdLaGgIR0CI1OaVD8cddX2UKGgGR8BS0Cz9jwx4aAdLZGgIR0CI1MkbgjyGdX2UKGgGR8BGKh7NSqEOaAdLY2gIR0CI1pttygf2dX2UKGgGR8BZ4+/gzguRaAdLcWgIR0CI1vZwn6VMdX2UKGgGR8BZ5v+GXXyzaAdLdmgIR0CI1qcDr7fpdX2UKGgGR8BXH27z06HTaAdLd2gIR0CI1967dznzdX2UKGgGR8BUN9lVcUudaAdLWWgIR0CI19Xr+o9+dX2UKGgGR8BIbsFEAo5QaAdLRmgIR0CI18jiXIEKdX2UKGgGR8BIa6Mir1dxaAdLaWgIR0CI145/9YOldX2UKGgGR8BUytkOI68yaAdLT2gIR0CI2Bc3VCokdX2UKGgGR8BXr2T1TR6XaAdLb2gIR0CI2AnhsImgdX2UKGgGR8BUjoyGi5/caAdLRWgIR0CI18cwxnFpdX2UKGgGR8BESg7HQyAQaAdLQ2gIR0CI2W54GD+SdX2UKGgGR8BHRbQswtaqaAdLVmgIR0CI2WXLvCuVdX2UKGgGR8BRtJPqLS/kaAdLe2gIR0CI2S3n6l+FdX2UKGgGR8BFd/aQFLWaaAdLRmgIR0CI2QWYWtU5dX2UKGgGR8BKOTkZJkGzaAdLb2gIR0CI2gkVvddndX2UKGgGR8BA8Y+r2g3+aAdLVGgIR0CI2b2ZAprldX2UKGgGR8BWOhpg1FYuaAdLXWgIR0CI2VOJtSAIdX2UKGgGR8BQr2E9Mbm2aAdLZmgIR0CI2UKl54W2dX2UKGgGR8BEFIKlYU35aAdLYmgIR0CI2ljx0+1SdX2UKGgGR8BWK2BWgezVaAdLhWgIR0CI21MrVe8gdX2UKGgGR8BOllxwQ176aAdLSmgIR0CI2r00WM0hdX2UKGgGR8BY/DNhVlwtaAdLg2gIR0CI2mg2ZRbbdX2UKGgGR8BJZbROUMXraAdLVWgIR0CI24NQTEiudX2UKGgGR8BRgAzpHI6saAdLXGgIR0CI22DrZ8KHdX2UKGgGR8BWED9jwx33aAdLcGgIR0CI20Gmk30gdX2UKGgGR8BRaCQgcLjQaAdLTmgIR0CI2yll9SdfdX2UKGgGR8Ai7mdRR/EwaAdLTmgIR0CI2x0SRKYidX2UKGgGR8BCoiCJ40MxaAdLUGgIR0CI2wYzi0fHdX2UKGgGR8BSOspw0fozaAdLZGgIR0CI3HLdvbXZdX2UKGgGR8BHbdz4k/r0aAdLkmgIR0CI3GXqqwQldX2UKGgGR8BRUV5v99+gaAdLcWgIR0CI3EzEaVD8dX2UKGgGR8BN2g2Q4jrzaAdLRGgIR0CI3BNZeRgadX2UKGgGR8BLJ3dKujh2aAdLXWgIR0CI29jxTbWVdX2UKGgGR8BPFzSkTHsDaAdLZGgIR0CI3OL3sXzldX2UKGgGR8BVYYI0IkZ8aAdLS2gIR0CI3JI6r/83dX2UKGgGR8BVndqHoHLSaAdLW2gIR0CI3G7qY7aJdX2UKGgGR8BVHFvES/TLaAdLcGgIR0CI3Gg9Net0dX2UKGgGR8BKqkEC/47BaAdLYmgIR0CI3C90zTF3dX2UKGgGR8BEl1IAfdRBaAdLbWgIR0CI3PyZrpJPdX2UKGgGR8BUoM9nscABaAdLZmgIR0CI3WMF2V3VdX2UKGgGR8BMBMbm2b5NaAdLbWgIR0CI3kyeI2wWdX2UKGgGR8BQW9YOlO45aAdLgmgIR0CI3k5vLowFdX2UKGgGR8BKk7a7EpAlaAdLW2gIR0CI3fM0P6KtdX2UKGgGR8BO72Kl54W2aAdLSWgIR0CI3fQDV6NVdX2UKGgGR8BSnsAFPi1iaAdLUGgIR0CI3fMgU1yedX2UKGgGR8BSDsp1A7gbaAdLgGgIR0CI3dmFJxvOdX2UKGgGR8BHNbMgU1yeaAdLf2gIR0CI3vpu/DcedX2UKGgGR8BT+4kNWluWaAdLZmgIR0CI3r1ct5D7dX2UKGgGR8A6iYdyT6i1aAdLjWgIR0CI38Fdszl+dX2UKGgGR8BIo8OCoS+QaAdLVmgIR0CI3zl0YCQtdX2UKGgGR8BDW2RzRx95aAdLVGgIR0CI4CS7oStedX2UKGgGR8BVuzgEU0vXaAdLZmgIR0CI37mJ3xFzdX2UKGgGR8BVk25paiblaAdLZGgIR0CI4Js67ulXdX2UKGgGR8BMhnjp9qk/aAdLTWgIR0CI4FfYSQHSdX2UKGgGR8BOZaOPvKEGaAdLXWgIR0CI4WXUpd8idX2UKGgGR8BKbdVmz0HyaAdLQmgIR0CI4UkD6nBMdX2UKGgGR8BQJlk+X7cgaAdLgWgIR0CI4WOJcgQpdX2UKGgGR8BRmNrKvFFVaAdLVGgIR0CI4qJ40Mw2dX2UKGgGR8BHV/H5rP+oaAdLl2gIR0CI4niI+GGmdX2UKGgGR8BTZ/CZWq95aAdLfmgIR0CI4lpDeCTVdX2UKGgGR8BJgEBjnV5KaAdLfWgIR0CI4vTd+G47dX2UKGgGR8A08zdDYywfaAdLhGgIR0CI4u6xPfsNdX2UKGgGR8BD+a1LJ0W/aAdLbGgIR0CI4puhsZYQdX2UKGgGR8Ac9xT850bMaAdLS2gIR0CI4kbONYKZdX2UKGgGR8BQ/s9B8hLXaAdLgmgIR0CI43vsqrimdX2UKGgGR8BV/Topx3mnaAdLdmgIR0CI5DxhDw6RdX2UKGgGR8BX9La/RE4OaAdLdGgIR0CI421KGtZFdX2UKGgGR8BOzrvLHMlkaAdLb2gIR0CI5IP+XJHRdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 16, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[ -2.5 -2.5 -10. -10. -6.2831855 -10.\n -0. -0. ]", "bounded_below": "[ True True True True True True True True]", "high": "[ 2.5 2.5 10. 10. 6.2831855 10.\n 1. 1. ]", "bounded_above": "[ True True True True True True True True]", "low_repr": "[ -2.5 -2.5 -10. -10. -6.2831855 -10.\n -0. -0. ]", "high_repr": "[ 2.5 2.5 10. 10. 6.2831855 10.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 256, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function RolloutBuffer.__init__ at 0x7f19457f42c0>", "reset": "<function RolloutBuffer.reset at 0x7f19457f4360>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f19457f4400>", "add": "<function RolloutBuffer.add at 0x7f19457f4540>", "get": "<function RolloutBuffer.get at 0x7f19457f45e0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f19457f4680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f19457805c0>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.0-134-generic-x86_64-with-glibc2.35 # 145-Ubuntu SMP Wed Feb 12 20:08:39 UTC 2025", "Python": "3.12.9", "Stable-Baselines3": "2.6.0", "PyTorch": "2.5.1+cu124", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "Gymnasium": "1.1.1", "OpenAI Gym": "0.26.2"}}
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f6d6bd92700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6d6bd927a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6d6bd92840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6d6bd928e0>", "_build": "<function ActorCriticPolicy._build at 0x7f6d6bd92980>", "forward": "<function ActorCriticPolicy.forward at 0x7f6d6bd92a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6d6bd92ac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6d6bd92b60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6d6bd92c00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6d6bd92ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6d6bd92d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6d6bd92de0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6d766fdec0>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1744137563006229533, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[ -2.5 -2.5 -10. -10. -6.2831855 -10.\n -0. -0. ]", "bounded_below": "[ True True True True True True True True]", "high": "[ 2.5 2.5 10. 10. 6.2831855 10.\n 1. 1. ]", "bounded_above": "[ True True True True True True True True]", "low_repr": "[ -2.5 -2.5 -10. -10. -6.2831855 -10.\n -0. -0. ]", "high_repr": "[ 2.5 2.5 10. 10. 6.2831855 10.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function RolloutBuffer.__init__ at 0x7f6d6bf502c0>", "reset": "<function RolloutBuffer.reset at 0x7f6d6bf50360>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f6d6bf50400>", "add": "<function RolloutBuffer.add at 0x7f6d6bf50540>", "get": "<function RolloutBuffer.get at 0x7f6d6bf505e0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f6d6bf50680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6d6bf07800>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.0-134-generic-x86_64-with-glibc2.35 # 145-Ubuntu SMP Wed Feb 12 20:08:39 UTC 2025", "Python": "3.12.9", "Stable-Baselines3": "2.6.0", "PyTorch": "2.5.1+cu124", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "Gymnasium": "1.1.1", "OpenAI Gym": "0.26.2"}}
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51058759663992911936990dce31f5a6d2e9fed6e0325acdaa827337122be5f2
3
- size 215339
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9668c1142570db8ab7aac676a46651d52520efb3cc4d3657d99e421793d64b
3
+ size 171295
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -135.79444540000003, "std_reward": 47.53708096018634, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-08T18:53:50.655422"}
 
1
+ {"mean_reward": 274.5040922, "std_reward": 26.720794202534982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-08T19:02:02.835372"}