Initial commit

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: dqn
+- name: ppo
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 195.09 +/- 86.70
+      value: 181.51 +/- 93.61
       name: mean_reward
       verified: false
 ---
 
-# **dqn** Agent playing **LunarLander-v2**
-This is a trained model of a **dqn** agent playing **LunarLander-v2**
+# **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)

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=", "__module__": "stable_baselines3.dqn.policies", "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}", "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\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 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 DQNPolicy.__init__ at 0x7ed49a109900>", "_build": "<function DQNPolicy._build at 0x7ed49a109990>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7ed49a109a20>", "forward": "<function DQNPolicy.forward at 0x7ed49a109ab0>", "_predict": "<function DQNPolicy._predict at 0x7ed49a109b40>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7ed49a109bd0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7ed49a109c60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ed49a111640>"}, "verbose": 0, "policy_kwargs": {"net_arch": [128, 128]}, "num_timesteps": 600000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698366233466265255, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAANPtfD6F2IU+K+JTPHCLFb2QHic+PeEbOgAAAAAAAAAA5vvqvUPmFj3f8Km+wKq2vJpOhbwIHf69AAAAAAAAAACzJbS9B0wCPvkPC75mbJO9Xql6PXdNwr0AAAAAAAAAAJpanT71oUQ/jY2TPtYfPr42s+w9pE2EPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAANrLfD4vRIY+K+JTPKtFIbzFFic+ft8bOgAAAAAAAAAAwA7kvfbyGD3TH6m+QpJbvf/3JLwbM/m9AAAAAAAAAACNRLG9zfUDPgYQC77NnDm9wguHPYpNwr0AAAAAAAAAAJrcmz5fs0U/cPGSPj06Qr65FeY9slpvPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwiGlIwBQ5R0lFKULg=="}, "_episode_num": 1519, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.400004, "_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": 34374, "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 4, "buffer_size": 1000000, "batch_size": 64, "learning_starts": 50000, "tau": 1.0, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function ReplayBuffer.__init__ at 0x7ed49a0e1cf0>", "add": "<function ReplayBuffer.add at 0x7ed49a0e1d80>", "sample": "<function ReplayBuffer.sample at 0x7ed49a0e1e10>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7ed49a0e1ea0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7ed49a0e1f30>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ed4b350d080>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.05, "exploration_fraction": 0.1, "target_update_interval": 10000, "_n_calls": 149999, "max_grad_norm": 10, "exploration_rate": 0.05, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7a6c16a4c5e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a6c16a4c670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a6c16a4c700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a6c16a4c790>", "_build": "<function ActorCriticPolicy._build at 0x7a6c16a4c820>", "forward": "<function ActorCriticPolicy.forward at 0x7a6c16a4c8b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a6c16a4c940>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a6c16a4c9d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7a6c16a4ca60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a6c16a4caf0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a6c16a4cb80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a6c16a4cc10>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a6c1ec26200>"}, "verbose": 0, "policy_kwargs": {"net_arch": [128, 128]}, "num_timesteps": 350000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698872500638066931, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZSJbzUF64/ynv2vbANob6O/FC7Cr0wvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.65184, "_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": 1700, "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db50d582f67ccb892120c8813e4c16f4a2c53666dd5b6b751400315acc4ee578
+size 461499

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

ppo-LunarLander-v2/data

@@ -0,0 +1,104 @@
+{
+    "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 0x7a6c16a4c5e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a6c16a4c670>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a6c16a4c700>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a6c16a4c790>",
+        "_build": "<function ActorCriticPolicy._build at 0x7a6c16a4c820>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7a6c16a4c8b0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a6c16a4c940>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a6c16a4c9d0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7a6c16a4ca60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a6c16a4caf0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a6c16a4cb80>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a6c16a4cc10>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7a6c1ec26200>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {
+        "net_arch": [
+            128,
+            128
+        ]
+    },
+    "num_timesteps": 350000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1698872500638066931,
+    "learning_rate": 0.001,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZSJbzUF64/ynv2vbANob6O/FC7Cr0wvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.65184,
+    "_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": 1700,
+    "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
+        "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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:": "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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71fce44aaa9b1e7204cc0bc4b61af9ef6f0d296e5df9b1ba3133abf4263c0ac
+size 297770

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de40e7b5cb50658e10486aee3209fc8bbbb29a4bd9c0bce56663a02bd6cc22c9
+size 148466

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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.1.0+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": 195.0912288, "std_reward": 86.7021386304236, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-27T01:02:35.378324"}
+{"mean_reward": 181.51370839999998, "std_reward": 93.60504340994076, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-01T21:37:40.231948"}