First hands on rl excersise

.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: 256.54 +/- 20.45
+      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 0x78f8a51ba340>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78f8a51ba3e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78f8a51ba480>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78f8a51ba520>", "_build": "<function ActorCriticPolicy._build at 0x78f8a51ba5c0>", "forward": "<function ActorCriticPolicy.forward at 0x78f8a51ba660>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78f8a51ba700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78f8a51ba7a0>", "_predict": "<function ActorCriticPolicy._predict at 0x78f8a51ba840>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78f8a51ba8e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78f8a51ba980>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78f8a51baa20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78f8a55726c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1755525105154582105, "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": 248, "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": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 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:bae69a4243af56e11cfb08613314cfacb5cc9805a4408ed273025d84393d448e
+size 148120

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 0x78f8a51ba340>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78f8a51ba3e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78f8a51ba480>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78f8a51ba520>",
+        "_build": "<function ActorCriticPolicy._build at 0x78f8a51ba5c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78f8a51ba660>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78f8a51ba700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78f8a51ba7a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78f8a51ba840>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78f8a51ba8e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78f8a51ba980>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78f8a51baa20>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78f8a55726c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1755525105154582105,
+    "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": 248,
+    "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": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "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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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0087250dac598ed81f7fa3fe3d64692a0255db7263d791ea81de873e98e1c7
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38d75b976514587230d27be8b6e4b9cad2a88ea6ee01de14e46ebf16fd8ebfcf
+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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 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 sha256:8625c5a8588fbd8a53e2fcc04fb6fd54cc2dd28e75990436043e77b94167c541
+size 144028

results.json

@@ -0,0 +1 @@
+{"mean_reward": 256.5376247, "std_reward": 20.446436962241624, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-18T14:17:19.771489"}