The first step of RL learningg!!!

.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: 275.73 +/- 19.77
+      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 0x7e756aec6de0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e756aec6e80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e756aec6f20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e756aec6fc0>", "_build": "<function ActorCriticPolicy._build at 0x7e756aec7060>", "forward": "<function ActorCriticPolicy.forward at 0x7e756aec7100>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e756aec71a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e756aec7240>", "_predict": "<function ActorCriticPolicy._predict at 0x7e756aec72e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e756aec7380>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e756aec7420>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e756aec74c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e756ae52880>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 150528, "_total_timesteps": 150000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1739735024419632766, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEpIgz6Hh1g/YO/QPneZUL9Ngu8+zBqvPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0035199999999999676, "_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": 4596, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "1.26.4", "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 sha256:66629973a530ee64e9a6c5407f086ad04fa229001e0e1fc59e6a85a26b1dce62
+size 147359

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 0x7e756aec6de0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e756aec6e80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e756aec6f20>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e756aec6fc0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7e756aec7060>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7e756aec7100>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e756aec71a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e756aec7240>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7e756aec72e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e756aec7380>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e756aec7420>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e756aec74c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7e756ae52880>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 150528,
+    "_total_timesteps": 150000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1739735024419632766,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEpIgz6Hh1g/YO/QPneZUL9Ngu8+zBqvPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0035199999999999676,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWV7QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG6I77CSA6OMAWyUS9+MAXSUR0Cke1saCL/CdX2UKGgGR0BxWVm29crzaAdNCAFoCEdApHwYR/ViF3V9lChoBkdAbk/Rm9QGfWgHS8FoCEdApHyl4HHFP3V9lChoBkdAcaVOwgTyrmgHTQ4BaAhHQKR9ZQQ+UyJ1fZQoaAZHQHGst+gDifhoB0veaAhHQKR9/05EMLF1fZQoaAZHQHHEhsVLzwtoB0vfaAhHQKR/Qcqe9SN1fZQoaAZHQHM3SGJvYOFoB00gAWgIR0CkgA0wztTldX2UKGgGR0BvkgdKdxyXaAdL0WgIR0CkgKOYQarFdX2UKGgGR0Bva4gLZzxPaAdL2GgIR0CkgTw4bS7YdX2UKGgGR0ByGRcGC7K8aAdL8mgIR0Ckgoa0Y0l7dX2UKGgGR0BwdT8wYcebaAdL3mgIR0CkgyTcqOLjdX2UKGgGR0Bw51mcvugIaAdL8mgIR0Ckg89PtUn5dX2UKGgGRz/+MiW3Sa3JaAdLn2gIR0CkhEPDYRNAdX2UKGgGR0BxDIEOiFj/aAdL+WgIR0CkhP94mkWRdX2UKGgGR0BypXustCiRaAdL0WgIR0CkhjA31jAjdX2UKGgGR0BxcV6fJ3gUaAdL4WgIR0CkhtLBj4HpdX2UKGgGR0BwO+ADq4YraAdL3WgIR0Ckh24WLxZudX2UKGgGR0Bx4oQRPGhmaAdL1GgIR0CkiAnh0hePdX2UKGgGR0BxG0qhDgIhaAdLx2gIR0CkiZuU2UB5dX2UKGgGR0BxUSVVxS5zaAdNAAFoCEdApIqAjW07bXV9lChoBkdAcZHSgoPTX2gHS+ZoCEdApItq4hEBsHV9lChoBkdAcwZ+xGDtgWgHS9poCEdApIwwVZcLSnV9lChoBkdAcS5WtEG7jGgHS+BoCEdApIzV85S3s3V9lChoBkdAcSB3Zwn6VWgHS9FoCEdApI4LZ13dK3V9lChoBkdAcucq1gH/tWgHTVoBaAhHQKSPCXO4XoF1fZQoaAZHQHDWT3qRlpZoB0vEaAhHQKSPk3pfQa91fZQoaAZHQHDo44hllK9oB0v4aAhHQKSQRfj0cwR1fZQoaAZHQG4g7fpD/l1oB0vjaAhHQKSRh4fOlft1fZQoaAZHQHD8fD+BH09oB0vEaAhHQKSSEgpz90l1fZQoaAZHQHD9K1Cw8nxoB0vSaAhHQKSSo3uuzQh1fZQoaAZHQHAODYAbQ1JoB0vUaAhHQKSTOW/JvHd1fZQoaAZHQHGngjUutfZoB0u5aAhHQKSTuapgkTp1fZQoaAZHQHBkaInBtUJoB0vzaAhHQKSVBrqMWGh1fZQoaAZHQHMsmluWKMxoB0voaAhHQKSVqbYsd1d1fZQoaAZHQHGKkEPlMh5oB002AmgIR0Ckl0aCL/CJdX2UKGgGR0ByQ+m65Gz9aAdLzmgIR0CkmHgA6uGLdX2UKGgGR0BxI8WvbGm2aAdL1WgIR0CkmRN3np0PdX2UKGgGR0BN+DJEH+qBaAdLm2gIR0CkmYBGYrrgdX2UKGgGR0Bxvf6j3225aAdL5WgIR0CkmiQBHTZydX2UKGgGR0BxbKwwCbMHaAdLtmgIR0CkmqaRZEDydX2UKGgGR0BvHoXEZR8/aAdLyWgIR0Ckm9i/oJRgdX2UKGgGR0BxjQ71ZkkKaAdL5GgIR0CknH0KArhBdX2UKGgGR0BxvNIxxkupaAdL62gIR0CknSxRl6JJdX2UKGgGR0BwH7c6/7BPaAdLxWgIR0CknbuDSPU8dX2UKGgGR0BwLooPTXrdaAdLwGgIR0CknkZmh/RWdX2UKGgGR0BtTvjuKGcnaAdLzGgIR0Ckn4AKv3ajdX2UKGgGR0BTxrGecx0uaAdLo2gIR0Ckn/rZSNwSdX2UKGgGR0BxRQmJFb3XaAdL3mgIR0CkoNWnTAnEdX2UKGgGR0BxfsYAKfFraAdL+WgIR0Ckoc3+l0o0dX2UKGgGR0BzKWs4ku6FaAdL7mgIR0CkorO+h4+sdX2UKGgGR0BL50OEug6EaAdLkGgIR0CkpDAV45cUdX2UKGgGR0BzCXVVghKUaAdNBQFoCEdApKTro8p1BHV9lChoBkdAcbJVENOM2mgHTQUBaAhHQKSlp1oxpL51fZQoaAZHQHIwRJ/XoTxoB0vKaAhHQKSmNdgv1151fZQoaAZHQHLXGYrrgO1oB0vbaAhHQKSnbZPl+3J1fZQoaAZHQHG1iH/LkjpoB0veaAhHQKSoE0ygwoN1fZQoaAZHQHJ7X9Nvfj1oB00BAWgIR0CkqMwwsXizdX2UKGgGR0Bvc3rSmZVoaAdL2GgIR0CkqWboKUmldX2UKGgGR0BxsyJN0vGqaAdL5GgIR0Ckqg5AhStOdX2UKGgGR0Bxdv2VVxS6aAdL5WgIR0Ckq1W8AaNudX2UKGgGR0Bw9DIKc/dJaAdL3mgIR0Ckq/o5YHPedX2UKGgGR0ByCr+T/yXlaAdL+2gIR0CkrK4RmK64dX2UKGgGR0Bwo9Q/HHWCaAdL4WgIR0CkrU83EQ5FdX2UKGgGR0Bygw6kqMFVaAdLw2gIR0Ckrn1MM7U5dX2UKGgGR0BxZLB2wFC+aAdL3WgIR0CkryQ2VE/jdX2UKGgGR0BvbfMbFS88aAdLxGgIR0Ckr62TgVGkdX2UKGgGR0ByVqQzUI9laAdLxWgIR0CksD6BiCrcdX2UKGgGR0BvjQhIOH32aAdL3mgIR0CksNswtapxdX2UKGgGR0BtsU6gdwNtaAdL1GgIR0CkshF3yI56dX2UKGgGR0BE0CUX531SaAdLoGgIR0CksoHdfsu4dX2UKGgGR0ByY7b349HMaAdLyWgIR0CksxGPHT7VdX2UKGgGR0BwQfNr0rbyaAdL5mgIR0Cks7F0xM37dX2UKGgGR0Bwwq9AX2ugaAdL32gIR0CktFPp6hQFdX2UKGgGR0BvzvK2a2F4aAdL5GgIR0CktZUvPC2udX2UKGgGR0Bw1vy/bj95aAdL3WgIR0CktjozFdcCdX2UKGgGR0BzPgTSLIgeaAdNFAFoCEdApLb+IhyKenV9lChoBkdAcYLZpSJj2GgHS+5oCEdApLep8c+7lXV9lChoBkdAcUD0vGp++mgHS+poCEdApLk+UD+zdHV9lChoBkdAcK/ub7TDwmgHS8JoCEdApLnuoegctHV9lChoBkdAcjKu0kWykmgHS/hoCEdApLrV0Rvm5nV9lChoBkdAca16PKdQPGgHS+hoCEdApLu+2Zy+6HV9lChoBkdAcqIGhmGucWgHS+ZoCEdApLyLwjMV13V9lChoBkdAcc1w4KhL5GgHS+NoCEdApL3KxmkFfXV9lChoBkdAcOVF23azvGgHS8xoCEdApL5gOz6acHV9lChoBkdAcGwnaFmFrWgHS/ZoCEdApL8SN6w+uHV9lChoBkdAbvcoo/iYLWgHS9toCEdApL+t2q1gIHV9lChoBkdAca8n4wh4dWgHS/ZoCEdApMD+lCTlk3V9lChoBkdAcF4lYlpoK2gHS9doCEdApMGY11nuiXV9lChoBkdActjna37UG2gHS+VoCEdApMI6SgXdkHV9lChoBkdAcGUSUkfLcWgHS9RoCEdApMLSwD/2kHV9lChoBkdAcpI12JSBLGgHTRoBaAhHQKTDls+mm+F1fZQoaAZHQHLIly7wrlNoB00CAWgIR0CkxPX36AOKdX2UKGgGR0BwxPIxQBPsaAdL7WgIR0CkxZ0xmCiAdX2UKGgGR0BwjFDQZ4wAaAdL5GgIR0Ckxj7cO9WZdX2UKGgGR0BwHJ6Uqx1QaAdLzWgIR0Ckxtc5jpcHdX2UKGgGR0Bx9fHzYmLMaAdL4GgIR0CkyBPECNjtdX2UKGgGR0BwjpoEjgQ6aAdNBgFoCEdApMjSCz1K5HV9lChoBkdAcG3AFPi1iWgHS9doCEdApMlo5tFa0XV9lChoBkdAcZLA7xNIsmgHS+JoCEdApMoH4ubqhXV9lChoBkdAcPODv3JxN2gHS+5oCEdApMqyvA44qHVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 4596,
+    "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "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:e0d1c231a87a6738c56d2b97c6d6f16939b27151fa8d115498f3907e6837fcc0
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4dc187958b297b9ead253a5663edc0179690b534518e06861e42964c06a761
+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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.11.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.5.1+cu124
+- GPU Enabled: True
+- Numpy: 1.26.4
+- 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 sha256:245763ef96aefcff7c1259bb4fb080a63903c6d33d85d5318e2f83bed14ae2e7
+size 184545

results.json

@@ -0,0 +1 @@
+{"mean_reward": 275.73396199999996, "std_reward": 19.76668260170407, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-16T19:53:01.930536"}