Upload PPO LunarLander-v2 trained agent with 1mln steps

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,28 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -42.89 +/- 30.54
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: 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)
+  TODO: Add your code
+  

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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f0aa0cf0d30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0aa0cf0dc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0aa0cf0e50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0aa0cf0ee0>", "_build": "<function ActorCriticPolicy._build at 0x7f0aa0cf0f70>", "forward": "<function ActorCriticPolicy.forward at 0x7f0aa0cf3040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0aa0cf30d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0aa0cf3160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0aa0cf31f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0aa0cf3280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0aa0cf3310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f0aa0ce5ba0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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, "system_info": {"OS": "Linux-5.17.5-arch1-1-x86_64-with-glibc2.17 #1 SMP PREEMPT Wed, 27 Apr 2022 20:56:11 +0000", "Python": "3.8.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "True", "Numpy": "1.21.5", "Gym": "0.21.0"}}

ppo-LunarLander-v2-1mln.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5c5296b3f0c67c31f81a5b021ed306d82f61fbd01b2a5ac4c655687c25d3ad
+size 143820

ppo-LunarLander-v2-1mln/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

ppo-LunarLander-v2-1mln/data

@@ -0,0 +1,94 @@
+{
+    "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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f0502e5a310>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0502e5a3a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0502e5a430>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0502e5a4c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0502e5a550>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0502e5a5e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0502e5a670>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0502e5a700>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0502e5a790>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0502e5a820>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0502e5a8b0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f0502e536c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652000220.1752121,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAC0yEj7ekrw+BhPrvQR0br4BiW89AjgTPQAAAAAAAAAATWZ+PVxkhj/eDKA9IoLIvgTMlT1UsBq9AAAAAAAAAADmq1o+rXK9PlXgA76eNoe+obmVPfDZFr0AAAAAAAAAADOuVj2l1Ac/jgHsvOXRlb4x5E08NT4cvQAAAAAAAAAA02wvvhPdxj6LklA+JzcrvgQyQjxvN4y8AAAAAAAAAADiZIS+G10cP1vxuj5/Kna+fBfGO677UT0AAAAAAAAAAM1YeTyJUD49pIwpvhPdUL7MTQ88k24DvQAAAAAAAAAATdQMPaevdj58jpi9nVY3vmqZ8Tte/1E9AAAAAAAAAABzxuU9/P+jP8prFT+6MvK+i4/ePXz6kz4AAAAAAAAAABNfPL5ryco+iLisPZlZXL4iyde8E0xSPAAAAAAAAAAAlut1vt6mDD+XYg8+xnNJvsi+NjwDec89AAAAAAAAAABmUkM9NWQVPnNZ273HPjO+52SrvDKBAL4AAAAAAAAAADPjqrvJgiw9QMaEvn0wP76gqMG9KbajvAAAAAAAAAAAAEpIvXsxnTu1GNg82XgDvuHvhbw7pio9AAAAAAAAAAAAU4C+zBieP1qI2L7tery+kGqTvtALab0AAAAAAAAAADPTUjupAWk+HloRPgl/c75darE9UKBkPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 248,
+    "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
+}

ppo-LunarLander-v2-1mln/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126d0ffdf9cd1639e63f5937848c4ddd348b1fdd45aeb84cda304b82ff919c01
+size 84573

ppo-LunarLander-v2-1mln/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26ec9ee4f77d95f2b78ff08099ec4ff820c50cdb0f160dab00f40f60cf1709d
+size 43073

ppo-LunarLander-v2-1mln/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2-1mln/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.17.5-arch1-1-x86_64-with-glibc2.17 #1 SMP PREEMPT Wed, 27 Apr 2022 20:56:11 +0000
+Python: 3.8.13
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0
+GPU Enabled: False
+Numpy: 1.21.5
+Gym: 0.21.0

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e43e96ec6f3ace5109cb8c9bcf9efe1426c9fbaa3d1b599e8a2c1574357111
+size 52885

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

ppo-LunarLander-v2/data

@@ -0,0 +1,82 @@
+{
+    "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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f0aa0cf0d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0aa0cf0dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0aa0cf0e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0aa0cf0ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0aa0cf0f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0aa0cf3040>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0aa0cf30d0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0aa0cf3160>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0aa0cf31f0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0aa0cf3280>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0aa0cf3310>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f0aa0ce5ba0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": null,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
+    "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
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab7f743c00d9fd8f6843d71d518a2be6a3427eb880347ab76205a81135ee5c8
+size 623

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8362ebb8d55a647f454741a2a0013d1990731c51b79aca1f704224108c897d97
+size 43201

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.17.5-arch1-1-x86_64-with-glibc2.17 #1 SMP PREEMPT Wed, 27 Apr 2022 20:56:11 +0000
+Python: 3.8.13
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.5
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -42.89330002684146, "std_reward": 30.536615733546483, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T22:16:12.547078"}