HF DRL: Unit 1

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: Proximal Policy Optimization with MLP PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 272.38 +/- 16.11
+      name: mean_reward
+      verified: false
+---
+
+# **Proximal Policy Optimization with MLP PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **Proximal Policy Optimization with MLP 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
+
+...
+```

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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7ff66ac61ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff66ac61f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff66ac68040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff66ac680d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff66ac68160>", "forward": "<function ActorCriticPolicy.forward at 0x7ff66ac681f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff66ac68280>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff66ac68310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff66ac683a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff66ac68430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff66ac684c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff66ac64240>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 819200, "_total_timesteps": 800000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671166879093341999, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAGBzAT5pHy89htcevlcVGL4lF6K97HiAPQAAAAAAAAAAzUOpvBZurD83N0O+PxLPvl+5Ubx+GK29AAAAAAAAAADAsbO95EuMP6Qxi75QNEy/svLGvQZIhL0AAAAAAAAAAGZF8bx7ppO6Ujd4NbEgSDCcRkE5Lt22tAAAgD8AAIA/QJqcPcORHLreEBs0JjV9L83AmzpfUrSzAACAPwAAgD+QfW6+OtToPpoojzztYxu/FD4ovs1Lpj0AAAAAAAAAAJOqWT7cYhs+6iFlvhfLXL7XGu67qD9QvQAAAAAAAAAAkwciPnUtSz41kfe9SV+RvlftqjzD+Pg7AAAAAAAAAADNzBK9FNiDuvo1oTaC5qAxNbKmOgIrvbUAAIA/AACAP41P/72wVyM/AZpKvh1NL796t/W9dc9kPAAAAAAAAAAADQKUPkIHqz6iX1u+SquZvmZ5+D14KxG+AAAAAAAAAADmk7C9Q90rPTFSyz6r2OO98aqnPZPWQz0AAAAAAAAAAIDrVD1Ia5q6/QXcs/U9Vy5T0de446+mMwAAgD8AAIA/Zq6PPGC4mz72rGO9hYzOvuchoLzSze69AAAAAAAAAABNyoC9KQgDujOFFD45drC4Na5puVUxqbcAAIA/AACAP42Pt713iV0/Cf1BvukSOL9D+dO9mgmUvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 320, "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, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

lunarlander_1_000_000_steps.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66024d9ddd231d2ab23e9d9a8b04f3823986a9eea7f0eefcdecc9142ec6a1eb
+size 147094

lunarlander_1_000_000_steps/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

lunarlander_1_000_000_steps/data

@@ -0,0 +1,94 @@
+{
+    "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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7ff66ac61ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff66ac61f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff66ac68040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff66ac680d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ff66ac68160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ff66ac681f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff66ac68280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ff66ac68310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff66ac683a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff66ac68430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff66ac684c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7ff66ac64240>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 819200,
+    "_total_timesteps": 800000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1671166879093341999,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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": -0.02400000000000002,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 320,
+    "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
+}

lunarlander_1_000_000_steps/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f417bcaf85de08bedbae9c51012cc259eaeaa67eed29626887b957c4ec410f
+size 87929

lunarlander_1_000_000_steps/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74acf21ecdf1764f495defbe4897b8d69729c0a90bf619f488b3eb99eadaf3d1
+size 43201

lunarlander_1_000_000_steps/pytorch_variables.pth

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

lunarlander_1_000_000_steps/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.8.16
+Stable-Baselines3: 1.6.2
+PyTorch: 1.13.0+cu116
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 272.3786005633409, "std_reward": 16.1095565698513, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-16T05:22:32.540557"}