first RL model!

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -968.42 +/- 454.65
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

apo_firstRL.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f675076908c19e52185f84efa4e4c822b730976cf776a49164a707baf7055c4
+size 145236

apo_firstRL/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

apo_firstRL/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7f0eddda77f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0eddda7880>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0eddda7910>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0eddda79a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0eddda7a30>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0eddda7ac0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0eddda7b50>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0eddda7be0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0eddda7c70>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0eddda7d00>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0eddda7d90>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0eddda7e20>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f0eddda9040>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 10240,
+    "_total_timesteps": 10000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1686865701043896619,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAI3i8j0J/44/omIVPzz8OL8JtI29TluWvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.02400000000000002,
+    "_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": 100,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    }
+}

apo_firstRL/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65b82bf30098d32f82a05adfbc5a3ba270027aeebacf18b194501f9b56607ea
+size 87929

apo_firstRL/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e627db6ac7f6b1638400e4353e2f5b4aa3172145c27eb375087f09bda9068c4
+size 43329

apo_firstRL/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

apo_firstRL/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

config.json

@@ -0,0 +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 0x7f0eddda77f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0eddda7880>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0eddda7910>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0eddda79a0>", "_build": "<function ActorCriticPolicy._build at 0x7f0eddda7a30>", "forward": "<function ActorCriticPolicy.forward at 0x7f0eddda7ac0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0eddda7b50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0eddda7be0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0eddda7c70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0eddda7d00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0eddda7d90>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0eddda7e20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0eddda9040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 10240, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1686865701043896619, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAI3i8j0J/44/omIVPzz8OL8JtI29TluWvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_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": 100, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -968.4219229, "std_reward": 454.65462690372846, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-15T21:50:16.788443"}