Improved 1.5e6 steps

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 257.22 +/- 21.14
+      value: 279.98 +/- 13.19
       name: mean_reward
       verified: false
 ---

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 0x7f867e976320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f867e9763b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f867e976440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f867e9764d0>", "_build": "<function ActorCriticPolicy._build at 0x7f867e976560>", "forward": "<function ActorCriticPolicy.forward at 0x7f867e9765f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f867e976680>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f867e976710>", "_predict": "<function ActorCriticPolicy._predict at 0x7f867e9767a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f867e976830>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f867e9768c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f867e976950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f867eb1f7c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1715265434057447300, "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:": "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x7bc3022e0160>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7bc3022e01f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7bc3022e0280>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7bc3022e0310>", "_build": "<function ActorCriticPolicy._build at 0x7bc3022e03a0>", "forward": "<function ActorCriticPolicy.forward at 0x7bc3022e0430>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7bc3022e04c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7bc3022e0550>", "_predict": "<function ActorCriticPolicy._predict at 0x7bc3022e05e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7bc3022e0670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7bc3022e0700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7bc3022e0790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bc30bb87400>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 1500160, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718641610091269148, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM105bti44c/yK1xvftV6L7vcKk8rbKfvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00010666666666669933, "_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": 5860, "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": 1, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+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 sha256:8174392494d169fcfd8fe9159731f3cc5fcb8b7dccdc1c6aa6a15a2be6d6c604
-size 148080
+oid sha256:207a17a112fcd63ac4b3c77c26874f62727497054068ac9fb69db53b66a6b82c
+size 147334

ppo-LunarLander-v2/data

@@ -4,54 +4,54 @@
         ":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 0x7f867e976320>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f867e9763b0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f867e976440>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f867e9764d0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f867e976560>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f867e9765f0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f867e976680>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f867e976710>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f867e9767a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f867e976830>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f867e9768c0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f867e976950>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7bc3022e0160>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7bc3022e01f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7bc3022e0280>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7bc3022e0310>",
+        "_build": "<function ActorCriticPolicy._build at 0x7bc3022e03a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7bc3022e0430>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7bc3022e04c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7bc3022e0550>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7bc3022e05e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7bc3022e0670>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7bc3022e0700>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7bc3022e0790>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f867eb1f7c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7bc30bb87400>"
     },
-    "verbose": 1,
+    "verbose": 0,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 1500160,
+    "_total_timesteps": 1500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1715265434057447300,
+    "start_time": 1718641610091269148,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM105bti44c/yK1xvftV6L7vcKk8rbKfvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": -0.00010666666666669933,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 248,
+    "_n_updates": 5860,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -76,7 +76,7 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 16,
+    "n_envs": 1,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9583a34113c6e2e53aae4b7bc18ff1b9c09b18179462b542d5ccc922a3880ccd
+oid sha256:c25a2a024b763775da3c65dee0537c368ee504a18d50f1e9d1128ff690ca17f9
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb22fded0f28c2749c8bc280f6ba444125ec97bcbb4dffc90772c638f784e5d
+oid sha256:b6fc828d90aca6873eceecbec0bab271cbd4baf728e955429326ed5379671e98
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -1,7 +1,7 @@
-- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
-- PyTorch: 2.2.1+cu121
+- PyTorch: 2.3.0+cu121
 - GPU Enabled: True
 - Numpy: 1.25.2
 - Cloudpickle: 2.2.1

results.json

@@ -1 +1 @@
-{"mean_reward": 257.22346480000004, "std_reward": 21.138875872736637, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-09T15:08:56.040498"}
+{"mean_reward": 279.97511249999997, "std_reward": 13.189076951167534, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-17T17:20:43.368465"}