rl course unit 1 workbook

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

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: 258.86 +/- 16.75
+      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
+
+...
+```

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 0x78d9ab373920>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78d9ab3739c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78d9ab373a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78d9ab373b00>", "_build": "<function ActorCriticPolicy._build at 0x78d9ab373ba0>", "forward": "<function ActorCriticPolicy.forward at 0x78d9ab373c40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78d9ab373ce0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78d9ab373d80>", "_predict": "<function ActorCriticPolicy._predict at 0x78d9ab373e20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78d9ab373ec0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78d9ab373f60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78d9ab37c040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78d9ab80f4c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1763384777932588617, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": 310, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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:": "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"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5632b5f594cfb60a52e3fc1eabccc6ac68978c219f6c0d1a9262d2d5877ef1e5
+size 148031

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/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 0x78d9ab373920>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78d9ab3739c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78d9ab373a60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78d9ab373b00>",
+        "_build": "<function ActorCriticPolicy._build at 0x78d9ab373ba0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78d9ab373c40>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78d9ab373ce0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78d9ab373d80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78d9ab373e20>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78d9ab373ec0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78d9ab373f60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78d9ab37c040>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78d9ab80f4c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1763384777932588617,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdgIAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAAIAAAAAAAAtpCm+g/Q7vOY9Ebz0/Fa6MymlPXrCMDsAAIA/AACAP0ZZRz4ypVQ+2TMWvoMloL7z3RS9KICNPQAAAAAAAAAAjVd3PkHtzbzdZXm74P+8Ob5UQr64NI46AACAPwAAgD8gST0+xcTIPAbjursd/k+60C5WPparYrsAAIA/AACAP6ZmWD5FL888aFc+urt+7LhxjmE+eXCBOQAAgD8AAIA/+vkGviQA5z5WZbs9VCervjrJ/Lwg/pc9AAAAAAAAAAANjAS+4fCouleNuznQxoU2qn0oPKKi57gAAIA/AACAPyByMT7DbTq8KIxjNZXFOLOmRZu9cqZdtAAAgD8AAIA/oPFBPk0wij/S4O8+p9H5vvYodT4L9Cw+AAAAAAAAAABmHkC98QYoPJoz8LzjpRW+kEkdvTajEz0AAAAAAAAAABqMML0RlsI94rYhPqf1QL4MlYI9rCquvAAAAAAAAAAA4FM5vnbIabx782S7SS+1uQUZ4D2L5JE6AACAPwAAgD+zn369e2agugN+5zSAvoou+4UOuoeiQrQAAIA/AACAP81QZT6FW9U8q9B2vD4RUDx/HoM+GzppvQAAgD8AAIA/INs/vtTnkrygO1I703SZObQDAT6edIW6AACAPwAAgD9zAjS+KcF2vMYmLrw8BpC6PXjQPaC8aDsAAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLEEsIhpSMAUOUdJRSlC4="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_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": 310,
+    "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c7dc118f9446eb9f80e12e30debc66a8df3952bfb3539a13ad0991634503ca
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec39bc49a15f2beb989444b27512d3e431b4e5329219ea2e370799bf725851a
+size 43762

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025
+- Python: 3.11.13
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.6.0+cu124
+- GPU Enabled: True
+- Numpy: 2.0.2
+- Cloudpickle: 3.1.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a729b2845ec7b6d37d2a76c7cc4c76d52cca65c91ddcde502301805374ab58bd
+size 103797

results.json

@@ -0,0 +1 @@
+{"mean_reward": 258.8564167, "std_reward": 16.753285799046342, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-17T13:50:22.721794"}