12FEB

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 190.50 +/- 38.01
+      value: 258.91 +/- 19.61
       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 0x794727200ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x794727200f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x794727201000>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x794727201090>", "_build": "<function ActorCriticPolicy._build at 0x794727201120>", "forward": "<function ActorCriticPolicy.forward at 0x7947272011b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x794727201240>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7947272012d0>", "_predict": "<function ActorCriticPolicy._predict at 0x794727201360>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7947272013f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x794727201480>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x794727201510>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7947271a4d00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1707753825256839432, "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": 0.18079999999999996, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 200, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "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"}, "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": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "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 0x7de9403b9360>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7de9403b93f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7de9403b9480>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7de9403b9510>", "_build": "<function ActorCriticPolicy._build at 0x7de9403b95a0>", "forward": "<function ActorCriticPolicy.forward at 0x7de9403b9630>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7de9403b96c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7de9403b9750>", "_predict": "<function ActorCriticPolicy._predict at 0x7de9403b97e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7de9403b9870>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7de9403b9900>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7de9403b9990>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7de9482c9000>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 828048, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1707763427108567617, "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": 0.18079999999999996, "_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": 200, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "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 sha256:19725010e527aaf88c6585662ec7d7cbebc4b645a2980aeab49dafb145adc333
-size 143920
+oid sha256:d87d8635a1b697729d5f28d811987692e5a3fd1c43049185d70c2ec42c04b5cd
+size 148069

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x794727200ee0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x794727200f70>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x794727201000>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x794727201090>",
-        "_build": "<function ActorCriticPolicy._build at 0x794727201120>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7947272011b0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x794727201240>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7947272012d0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x794727201360>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7947272013f0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x794727201480>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x794727201510>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7de9403b9360>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7de9403b93f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7de9403b9480>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7de9403b9510>",
+        "_build": "<function ActorCriticPolicy._build at 0x7de9403b95a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7de9403b9630>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7de9403b96c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7de9403b9750>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7de9403b97e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7de9403b9870>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7de9403b9900>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7de9403b9990>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7947271a4d00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7de9482c9000>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
+    "num_timesteps": 828048,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1707753825256839432,
+    "start_time": 1707763427108567617,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0f2e0748aca1045d9ed4fb14635deed9d5689be9d7289f7c7654e4e3a35646
+oid sha256:827acded1d8860d5cd1052325bb7ef0ce0366dc6cfea5a7ecf1d5c3dadbdbb79
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc6fcb54b7b693d7cb711e8baa0ed8047977e5ffb45a9199de47e0c964cee69
+oid sha256:5c2daee1304d17999d727a54385c5f61c017090835fbd86a408c8f78c31de93f
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 190.49779769999998, "std_reward": 38.00987598154954, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-12T16:32:59.207045"}
+{"mean_reward": 258.91281860000004, "std_reward": 19.607300672176216, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-12T19:03:34.220619"}