total_timesteps=1000000

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -606.83 +/- 156.16
+      value: 278.45 +/- 27.62
       name: mean_reward
     task:
       type: reinforcement-learning

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 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 0x7f4a6de524d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4a6de52560>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4a6de525f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4a6de52680>", "_build": "<function ActorCriticPolicy._build at 0x7f4a6de52710>", "forward": "<function ActorCriticPolicy.forward at 0x7f4a6de527a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4a6de52830>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4a6de528c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4a6de52950>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4a6de529e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4a6de52a70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f4a6dea2390>"}, "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": 32, "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:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
+{"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 0x7fc8c2cd58c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc8c2cd5950>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc8c2cd59e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc8c2cd5a70>", "_build": "<function ActorCriticPolicy._build at 0x7fc8c2cd5b00>", "forward": "<function ActorCriticPolicy.forward at 0x7fc8c2cd5b90>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc8c2cd5c20>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc8c2cd5cb0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc8c2cd5d40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc8c2cd5dd0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc8c2cd5e60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fc8c2d15e40>"}, "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": 1652381395.4142902, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 620, "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": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2_3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3265d320ae2c81974973773058f73e74e3866c90ec6800b96184e85d74d92bd
+size 144019

ppo-LunarLander-v2_3/_stable_baselines3_version

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

ppo-LunarLander-v2_3/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 0x7fc8c2cd58c0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc8c2cd5950>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc8c2cd59e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc8c2cd5a70>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc8c2cd5b00>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc8c2cd5b90>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc8c2cd5c20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc8c2cd5cb0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc8c2cd5d40>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc8c2cd5dd0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc8c2cd5e60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fc8c2d15e40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "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": 1652381395.4142902,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 620,
+    "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": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-LunarLander-v2_3/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:578fd75351fd32f5dba42e088e36772ed3b26205041bafc466b1fdde967fb020
+size 84893

ppo-LunarLander-v2_3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dffff9d162b12f0ae21eb46e2d3fb2f455a37af350a54c49590d58c8be453e5
+size 43201

ppo-LunarLander-v2_3/pytorch_variables.pth

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

ppo-LunarLander-v2_3/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5f727ef0180f0b2ef9de6736134ad2cef5051a885bfaf7bdeb32edb254eb5e
-size 270731
+oid sha256:15b0996b17412d227ee306280afa810a8bb09723e3578438863783efa6ee3164
+size 236100

results.json

@@ -1 +1 @@
-{"mean_reward": -606.8252502076327, "std_reward": 156.1645887003928, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T03:05:44.390677"}
+{"mean_reward": 278.4485894497471, "std_reward": 27.62268798891371, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T19:32:23.721307"}