Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 260.45 +/- 18.52
+      value: 267.46 +/- 16.00
       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 0x7f676e8d0430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f676e8d04c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f676e8d0550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f676e8d05e0>", "_build": "<function ActorCriticPolicy._build at 0x7f676e8d0670>", "forward": "<function ActorCriticPolicy.forward at 0x7f676e8d0700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f676e8d0790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f676e8d0820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f676e8d08b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f676e8d0940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f676e8d09d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f676e8d0a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f676e8d43c0>"}, "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": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677697056298865078, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAABdiDzDoTC63quHtHw4Uy/h1pA6M7WXMwAAgD8AAIA/JqdHvrxnij/SYMy+AaOxvkN5I76iABq+AAAAAAAAAADaU42+7gj7vMILhL2zqDm6OUpnPsKagjwAAAAAAAAAAJqb07zXIz25AtkNO62pHTiWCgA7DN0pugAAgD8AAIA/AHdfvSkoZLqTcYO5M1m4s4GmBLqY2ZY4AACAPwAAgD+AZrS9ce0BuQcMkTrX5Ys1TqfLO7Q0sbkAAAAAAACAP+blkz0d2s0+onT1vWOwb74kBXe9GVuyvAAAAAAAAAAAZh+kvNdESbtuJmK8Xkm6PNJCujwgOJ69AACAPwAAgD+a1im97JG+u8wjo7wfcI08OlcLvRC5bz0AAIA/AACAPwAsvruFA/O5niVevOPdtLspGU+6G1D/PAAAgD8AAAAAXauSPgJGaz8EAsU97AOVvj1qJT5c9xW+AAAAAAAAAADNLZq8CidQuXUOQbynQIe4Nyk/u13c+TcAAIA/AACAP2ZYcLxMc78/giYKvjtWVj4Xa4g8/UD3PAAAAAAAAAAAMxPdPBSUl7pCIAs4l983M8T+87hCex+3AACAPwAAgD8zo4M8KSRNuqZUHzkzTk02S/YkuygWPrgAAIA/AACAP00eZD2Fk725LnpLte9QSa9qT7C7vY5TNAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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, "system_info": {"OS": "Linux-5.15.79.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 # 1 SMP Wed Nov 23 01:01:46 UTC 2022", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.23.5", "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 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 0x7ffb26f80430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffb26f804c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffb26f80550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffb26f805e0>", "_build": "<function ActorCriticPolicy._build at 0x7ffb26f80670>", "forward": "<function ActorCriticPolicy.forward at 0x7ffb26f80700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffb26f80790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffb26f80820>", "_predict": "<function ActorCriticPolicy._predict at 0x7ffb26f808b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffb26f80940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffb26f809d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffb26f80a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ffb26f6fe40>"}, "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": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677697056298865078, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV+QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMYy9ob21lL2FwcGxldGVybml0eS9hbmFjb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMYy9ob21lL2FwcGxldGVybml0eS9hbmFjb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAABdiDzDoTC63quHtHw4Uy/h1pA6M7WXMwAAgD8AAIA/JqdHvrxnij/SYMy+AaOxvkN5I76iABq+AAAAAAAAAADaU42+7gj7vMILhL2zqDm6OUpnPsKagjwAAAAAAAAAAJqb07zXIz25AtkNO62pHTiWCgA7DN0pugAAgD8AAIA/AHdfvSkoZLqTcYO5M1m4s4GmBLqY2ZY4AACAPwAAgD+AZrS9ce0BuQcMkTrX5Ys1TqfLO7Q0sbkAAAAAAACAP+blkz0d2s0+onT1vWOwb74kBXe9GVuyvAAAAAAAAAAAZh+kvNdESbtuJmK8Xkm6PNJCujwgOJ69AACAPwAAgD+a1im97JG+u8wjo7wfcI08OlcLvRC5bz0AAIA/AACAPwAsvruFA/O5niVevOPdtLspGU+6G1D/PAAAgD8AAAAAXauSPgJGaz8EAsU97AOVvj1qJT5c9xW+AAAAAAAAAADNLZq8CidQuXUOQbynQIe4Nyk/u13c+TcAAIA/AACAP2ZYcLxMc78/giYKvjtWVj4Xa4g8/UD3PAAAAAAAAAAAMxPdPBSUl7pCIAs4l983M8T+87hCex+3AACAPwAAgD8zo4M8KSRNuqZUHzkzTk02S/YkuygWPrgAAIA/AACAP00eZD2Fk725LnpLte9QSa9qT7C7vY5TNAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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, "system_info": {"OS": "Linux-5.15.79.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 # 1 SMP Wed Nov 23 01:01:46 UTC 2022", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfb4e5054e03ff471bff2cd4f305bd6dad1c4cd6bee8fc27eb1b5c38f2b59ff
+oid sha256:741f0d557df07a8446d9c9842f55641aea44abe55e9c41323525a16c65353f4b
 size 147731

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x7f676e8d0430>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f676e8d04c0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f676e8d0550>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f676e8d05e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f676e8d0670>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f676e8d0700>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f676e8d0790>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f676e8d0820>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f676e8d08b0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f676e8d0940>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f676e8d09d0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f676e8d0a60>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ffb26f80430>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffb26f804c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffb26f80550>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffb26f805e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ffb26f80670>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ffb26f80700>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffb26f80790>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffb26f80820>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ffb26f808b0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffb26f80940>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffb26f809d0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffb26f80a60>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f676e8d43c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ffb26f6fe40>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 260.4533400056382, "std_reward": 18.5188427995261, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-01T14:43:51.509424"}
+{"mean_reward": 267.4620575118535, "std_reward": 16.004477702461312, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-01T14:46:41.141707"}