Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -173.47 +/- 52.87
+      value: -184.98 +/- 31.93
       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 0x7f17fcbde710>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f17fcbde7a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f17fcbde830>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f17fcbde8c0>", "_build": "<function ActorCriticPolicy._build at 0x7f17fcbde950>", "forward": "<function ActorCriticPolicy.forward at 0x7f17fcbde9e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f17fcbdea70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f17fcbdeb00>", "_predict": "<function ActorCriticPolicy._predict at 0x7f17fcbdeb90>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f17fcbdec20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f17fcbdecb0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f17fcbded40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f17fcb857c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710735764854865225, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM27qL179Lg5JJQ5O18JhrkrQ2o7nQFZugAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0035199999999999676, "_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": 396, "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-6.1.58+-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": "False", "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 0x7f17fcbde710>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f17fcbde7a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f17fcbde830>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f17fcbde8c0>", "_build": "<function ActorCriticPolicy._build at 0x7f17fcbde950>", "forward": "<function ActorCriticPolicy.forward at 0x7f17fcbde9e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f17fcbdea70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f17fcbdeb00>", "_predict": "<function ActorCriticPolicy._predict at 0x7f17fcbdeb90>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f17fcbdec20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f17fcbdecb0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f17fcbded40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f17fcb857c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710736432471641488, "learning_rate": 0.0, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM27qL179Lg5JJQ5O18JhrkrQ2o7nQFZugAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0035199999999999676, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 396, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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": "2.2.1+cu121", "GPU Enabled": "False", "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:e7f60a02dff991fd55b96c3d55842d5dcaeae112e9028de6d91e7565d1e8916d
-size 146831
+oid sha256:a185b63cbc440c7e290910a452fd1084cbac62811725e6ee32035ad0caefd3dd
+size 142468

ppo-LunarLander-v2/data

@@ -21,13 +21,13 @@
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 100352,
-    "_total_timesteps": 100000,
+    "num_timesteps": 0,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1710735764854865225,
-    "learning_rate": 0.0003,
+    "start_time": 1710736432471641488,
+    "learning_rate": 0.0,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,13 +45,28 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 396,
+    "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,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,7 +84,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -77,23 +92,8 @@
         "_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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"
+        ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURwAAAAAAAAAAhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
     }
 }

results.json

@@ -1 +1 @@
-{"mean_reward": -173.4668684, "std_reward": 52.873650283377636, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-18T04:32:13.611051"}
+{"mean_reward": -184.98119160000002, "std_reward": 31.926750507208464, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-18T04:34:20.475093"}