Upload PPO LunarLander-v2 trained agent - RL Course Unit 1 HandsOn Exercise

README.md

@@ -1,11 +1,10 @@
 ---
+library_name: stable-baselines3
 tags:
 - LunarLander-v2
-- ppo
 - deep-reinforcement-learning
 - reinforcement-learning
-- custom-implementation
-- deep-rl-course
+- stable-baselines3
 model-index:
 - name: PPO
   results:
@@ -17,45 +16,22 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -261.07 +/- 132.46
+      value: -679.60 +/- 267.10
       name: mean_reward
       verified: false
 ---
 
-  # PPO 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).
 
-  This is a trained model of a PPO agent playing LunarLander-v2.
+## Usage (with Stable-baselines3)
+TODO: Add your code
 
-  # Hyperparameters
-  ```python
-  {'exp_name': 'ppo'
-'seed': 1
-'torch_deterministic': True
-'cuda': True
-'track': False
-'wandb_project_name': 'cleanRL'
-'wandb_entity': None
-'capture_video': False
-'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.0002
-'num_envs': 4
-'num_steps': 128
-'anneal_lr': True
-'gae': True
-'gamma': 0.99
-'gae_lambda': 0.96
-'num_minibatches': 4
-'update_epochs': 4
-'norm_adv': True
-'clip_coef': 0.2
-'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
-'repo_id': 'guirnd/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
-  ```
-  
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -1 +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 0x7f60929b7490>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f60929b7520>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f60929b75b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f60929b7640>", "_build": "<function ActorCriticPolicy._build at 0x7f60929b76d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f60929b7760>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f60929b77f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f60929b7880>", "_predict": "<function ActorCriticPolicy._predict at 0x7f60929b7910>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f60929b79a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f60929b7a30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f60929b7ac0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f609295f940>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705670892021592027, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "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 0x7b2538013e20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2538013eb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2538013f40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2538020040>", "_build": "<function ActorCriticPolicy._build at 0x7b25380200d0>", "forward": "<function ActorCriticPolicy.forward at 0x7b2538020160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b25380201f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2538020280>", "_predict": "<function ActorCriticPolicy._predict at 0x7b2538020310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b25380203a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2538020430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b25380204c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b253892b480>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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": 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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bf9edd51dccfd6fb236f45567932bce111b524e58e5d83f8b3af987b4b4b28
-size 148064
+oid sha256:3060c1f4203769b5270baf97efc70df24092b94399f90457143afa3f7aa12519
+size 55178

ppo-LunarLander-v2/data

@@ -4,57 +4,45 @@
         ":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 0x7f60929b7490>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f60929b7520>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f60929b75b0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f60929b7640>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f60929b76d0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f60929b7760>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f60929b77f0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f60929b7880>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f60929b7910>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f60929b79a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f60929b7a30>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f60929b7ac0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7b2538013e20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2538013eb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2538013f40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2538020040>",
+        "_build": "<function ActorCriticPolicy._build at 0x7b25380200d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7b2538020160>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b25380201f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2538020280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7b2538020310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b25380203a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2538020430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b25380204c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f609295f940>"
+        "_abc_impl": "<_abc._abc_data object at 0x7b253892b480>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1705670892021592027,
+    "start_time": 0.0,
     "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
-    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": 1.0,
     "_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,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":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]",
@@ -69,7 +57,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
         "n": "4",
         "start": "0",
         "_shape": [],

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7707c6648cee7167ae0153512b6d06490b11790ea94fcfc829ea9ef1057cf4
-size 88362
+oid sha256:13dbf41e305d3a0b52e13b973ece0bb28ffca5bcf57636bcf9b68102feec544e
+size 1120

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf205cb2e9ba94a9e2c66f2f350f8fedd08e93b6f7d62eaba5ad81f8353d0e3
+oid sha256:54fdcee2ded687ee5b6afdcf9b5953281d724fe7c9992623feb40a3a88559911
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -3,7 +3,7 @@
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.1.0+cu121
 - GPU Enabled: True
-- Numpy: 1.23.5
+- Numpy: 1.25.2
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1
 - OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -261.0670706126897, "std_reward": 132.4598373592412, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-22T19:20:32.838135"}
+{"mean_reward": -679.5991593, "std_reward": 267.0955254601165, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-22T20:58:49.180134"}