One more try!

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 280.58 +/- 16.13
+      value: 286.34 +/- 10.43
       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 0x7f07385125f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0738512680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0738512710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f07385127a0>", "_build": "<function ActorCriticPolicy._build at 0x7f0738512830>", "forward": "<function ActorCriticPolicy.forward at 0x7f07385128c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0738512950>", "_predict": "<function ActorCriticPolicy._predict at 0x7f07385129e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0738512a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0738512b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0738512b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f07385157c0>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 64, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652378866.9388123, "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:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.995, "ent_coef": 0.005, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.16.3-microsoft-standard-WSL2-x86_64-with-glibc2.31 #1 SMP Fri Apr 2 22:23:49 UTC 2021", "Python": "3.10.4", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "True", "Numpy": "1.21.5", "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 0x7fb0ecdd65f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb0ecdd6680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb0ecdd6710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb0ecdd67a0>", "_build": "<function ActorCriticPolicy._build at 0x7fb0ecdd6830>", "forward": "<function ActorCriticPolicy.forward at 0x7fb0ecdd68c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb0ecdd6950>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb0ecdd69e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb0ecdd6a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb0ecdd6b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb0ecdd6b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb0ecdd1f40>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 64, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652482324.798781, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV+QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGQvaG9tZS9uYWRpcmJla292L2FuYWNvbmRhMy9lbnZzL2hmLXJsL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxkL2hvbWUvbmFkaXJiZWtvdi9hbmFjb25kYTMvZW52cy9oZi1ybC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoF2gOjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGIwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "n_steps": 1024, "gamma": 0.9945, "gae_lambda": 0.995, "ent_coef": 0.005, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.16.3-microsoft-standard-WSL2-x86_64-with-glibc2.31 #1 SMP Fri Apr 2 22:23:49 UTC 2021", "Python": "3.10.4", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "True", "Numpy": "1.21.5", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab1fce010a6e4fb7f4f6164d262b6bfb83815ec888ab742a97a99e005971cd62
-size 146297
+oid sha256:d60d020c86301ec44e9c90fed32f51f9a43d6188e7c40e6628ef11326a941835
+size 146289

ppo-LunarLander-v2/data

@@ -4,19 +4,19 @@
         ":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 0x7f07385125f0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0738512680>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0738512710>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f07385127a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f0738512830>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f07385128c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0738512950>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f07385129e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0738512a70>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0738512b00>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0738512b90>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fb0ecdd65f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb0ecdd6680>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb0ecdd6710>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb0ecdd67a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb0ecdd6830>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb0ecdd68c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb0ecdd6950>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb0ecdd69e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb0ecdd6a70>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb0ecdd6b00>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb0ecdd6b90>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f07385157c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fb0ecdd1f40>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -47,7 +47,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1652378866.9388123,
+    "start_time": 1652482324.798781,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -56,7 +56,7 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVdQgAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYACAAAAAAAAGa2U7x5mJs+trkAvrHlyb5mqKS9VvQJvgAAAAAAAAAAzZG+vCSUsj+Ai+69lf2ZviSPwLymn6U7AAAAAAAAAACA4nY9nbZIPspWAr6eooS+vwWtPOu/Kb0AAAAAAAAAAO2vjT4wdME+4lxevkNIHb8bu9E+3Tw/vgAAAAAAAAAAMz+QPesp1z1uCdW9RpWDvm5sgDtyR5y9AAAAAAAAAABmp369e3KOuioulrkV3A60ZDQLOgT0rDgAAIA/AACAP7NqDT6eH4Y/5QGzPlxwIb8JSmw+DWEZPgAAAAAAAAAAANpOPHG1CbuV9OW7TbmjvZolS7zbSMK+AACAPwAAgD8Y6I6+fM8PPxqEGz4JQg2/dMqgvh0WYj4AAAAAAAAAAM2eSbz0Yy8+bXIcPlmWnL6v6DA9+IyqPAAAAAAAAAAA5hkNvVyTYLr6PVQ+0UFVO8hCZbp/UTo8AAAAAAAAAACzEzU9e4CqukCXYD5Vkpk83UBpu4QVhT0AAIA/AACAP5oZaDt7Fpa6LtYHtCkTPa1OiNM6QXezMwAAgD8AAIA/s5EjPf+GZT9CoMM9swhJvw8K6jzzsAg7AAAAAAAAAAAAHzA+a2oiPwq3mj1mBgG/Zto6Pnbipr0AAAAAAAAAAIARLr1gE9E+ctkSPltF4r57f/88yzfYPQAAAAAAAAAAQ3KRPg6SRj/bAzE+PZL4vl9vzj7QK4C9AAAAAAAAAACAewo+YrisP3vpIT/LmMe+XRYzPm7lnz4AAAAAAAAAANrZFz6OSmg/m+VyPgfHI78tzGQ+/mtEvAAAAAAAAAAAWvm9Paj1nj3qCRG+pUoyvv280D3tkhi+AAAAAAAAAAAAHM28XFNJuqs53T1HCCaz1FoLuRbLHbMAAIA/AACAP1oU6z0j52w/A1BgPr1BNL/pcWU+0vPUPAAAAAAAAAAAurhwPsTiWD7WHqW+sW+pvoIvWDxFfIi9AAAAAAAAAAAGOms+P7IaP/VtqLwXDQ2/OLSNPjY8Cr4AAAAAAAAAAADgJz6HQZM/tSHBPvOTHb9aJpI+R5ubPQAAAAAAAAAAM6KlPL9lWz9eYPY7FotIv+P+Sz3SZCW8AAAAAAAAAABmwh68j1dnvKW1YT3DFdC8vOHGvV51x74AAIA/AACAPzNbirtSLN67QrDAvBmvOTwzZgi9bGI4OwAAgD8AAIA/Wh+jPW9EOz93Xw8+knQxv3S/6D2drkI9AAAAAAAAAABaq50+nzOePyXG0T7+hxm/9mn3PiJBmT0AAAAAAAAAAJphajyhCQM+MyWGuw1jrr6KJIE8YrTGPAAAAAAAAAAALfsaPsfNXD4ixU++HOSOvp3fWT2bjum9AAAAAAAAAAAmzYw94YCCut3lqjA1n4SwhUlLu0rINrIAAIA/AACAPzOH2rzfObw8zHOLvWJKGL6Wdma96dcbvQAAAAAAAAAAM0LdPBSXqT8EOI0+vAYIv8Ed+Dwphxo+AAAAAAAAAABmOiG9ff27P1HXCb/39JI+PjmzPDIsPr0AAAAAAAAAAM02nzxIF5G66osHPr8fXTET3187g2IMswAAgD8AAIA/yNeJvpdhbj9jZP2+w5ctv/VU6L4azte9AAAAAAAAAADqH66+7QLtPh4pOT5wgya/8qGzvltGcj4AAAAAAAAAAEbJWD7x7eQ9hR39vi/Ior7noBM+KPKZvgAAAAAAAAAAM5XzPBSsprquIuG1KSbTsAKG0Lg+XwY1AACAPwAAgD/tmxa+wMB8P7jcm74n8T6/IIqDvtVmmL0AAAAAAAAAACY/v73YNY4/oniNvnMRRL84EjO+A48TvQAAAAAAAAAAzcGDPIOJTj0a6US+9DSZvrOaF76w22G7AAAAAAAAAABmRCm+lKyGP2iJbr6V3Di/JFqNvqgwd70AAAAAAAAAAJqxRztcw3K62iErPR6yGD0z0pq6IPnNuwAAgD8AAIA/gMaSvQv+7j2t3kU+U0ifvvO+KDwwIeI9AAAAAAAAAAAzB6M7XJslujoJ0jY8oLKwa6qSu1WL97UAAIA/AACAP+acAj3DgKg/IIzaPmokLr+222Q4kEfsPQAAAAAAAAAAmjsEPYX62zwoYwC+m5CZvkETXb4ToaE9AAAAAAAAAACaeyw8KUxVuh2Or7MqNYCuLUKHO8pTyTMAAIA/AACAP5oynzwDUrU/3qZlPr5lfL0r5qA8RTXpPQAAAAAAAAAAGhqzveT7DT6o0Ok9Dz94vsvhBDzAyXQ9AAAAAAAAAADzRck9aAL8PY93m753UJG+KPMovpqFDzwAAAAAAAAAAM1bHT3fAoc8kQubvZIPJr53fiG9DgdFPQAAAAAAAAAAANeXvTwSLj1Wa5o9paWMvh8WKL3e6HU8AAAAAAAAAACzR/a9wWHCPS4XrD7JxV6+CbYtPnteWbwAAAAAAAAAAA2ujj2nbZU/rQGAPm1EJr/yXQM+UcrIPQAAAAAAAAAA5oiIPfb8WrrM9yczoMPyrouxhTnY/MmzAACAPwAAgD8gCnA+0DIlPyhBWr3wPwu/6LSJPib2rb0AAAAAAAAAAM1yCrwb7Iy84AmpPiqwvjvxOf4905aovAAAAAAAAIA/mnXIuzHakT8SxIC8qXlDv7Xui7yDRC29AAAAAAAAAAAzi4o9UumGP5YpCT7GMzC/fJnPPWawgDwAAAAAAAAAAACMJb3hBKG6WKRoumJHXrV89po6SQGGOQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYktASwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -69,7 +69,7 @@
     "_current_progress_remaining": -0.004885333333333408,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -77,7 +77,7 @@
     },
     "_n_updates": 368,
     "n_steps": 1024,
-    "gamma": 0.999,
+    "gamma": 0.9945,
     "gae_lambda": 0.995,
     "ent_coef": 0.005,
     "vf_coef": 0.5,
@@ -86,7 +86,7 @@
     "n_epochs": 8,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "gAWV+wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGQvaG9tZS9uYWRpcmJla292L2FuYWNvbmRhMy9lbnZzL2hmLXJsL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMEAIAA35SMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGQvaG9tZS9uYWRpcmJla292L2FuYWNvbmRhMy9lbnZzL2hmLXJsL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef1c8ad112a50edf305b6edd592d1425c3696e1367b4a27b84f2d671c777d87
+oid sha256:6cc30f34ac2323c14724bc9d8abf3dc350ef193a6f19ec6dcda6b6669bc5cc79
 size 84893

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0aaeaf1cc6272fd56d2a4a4e2e0ba1b552046dd864c7b5c0b31a3841dafdfb7
+oid sha256:a778555c8d99128ee67597082208eb5932bf1cd57d5725394c3fa0b3905d5fd2
 size 43201

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283f01d9712ed7b8fdd1b2213f5a373f503a2608c7f13dc8b32011514be46be9
-size 187838
+oid sha256:664d5eeb7b509c6fae96702812f9de68bc0b85645c534ab3b9453f02e9b50df5
+size 199050

results.json

@@ -1 +1 @@
-{"mean_reward": 280.5823631041261, "std_reward": 16.128313581977128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T23:00:04.406103"}
+{"mean_reward": 286.3427264456292, "std_reward": 10.429170471422553, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-14T12:36:13.726186"}