Upload PPO LunarLander-v2 trained agent - RL Course Unit 1 HandsOn Exercise

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -679.60 +/- 267.10
+      value: -214.06 +/- 75.07
       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 0x7b2538013e20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2538013eb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2538013f40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2538020040>", "_build": "<function ActorCriticPolicy._build at 0x7b25380200d0>", "forward": "<function ActorCriticPolicy.forward at 0x7b2538020160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b25380201f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2538020280>", "_predict": "<function ActorCriticPolicy._predict at 0x7b2538020310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b25380203a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2538020430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b25380204c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b253892b480>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": "1.25.2", "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 0x79b8f59fc310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79b8f59fc3a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79b8f59fc430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79b8f59fc4c0>", "_build": "<function ActorCriticPolicy._build at 0x79b8f59fc550>", "forward": "<function ActorCriticPolicy.forward at 0x79b8f59fc5e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79b8f59fc670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79b8f59fc700>", "_predict": "<function ActorCriticPolicy._predict at 0x79b8f59fc790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79b8f59fc820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79b8f59fc8b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79b8f59fc940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79b8f5a00380>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1708635768792101284, "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": -0.1468799999999999, "_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": 33, "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:": "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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": "1.25.2", "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 sha256:3060c1f4203769b5270baf97efc70df24092b94399f90457143afa3f7aa12519
-size 55178
+oid sha256:aeb00abd2713daf97e595b34f543850bdb702814c7bed4b2c7df8a5c4ce7e897
+size 147951

ppo-LunarLander-v2/data

@@ -4,42 +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 0x7b2538013e20>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2538013eb0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2538013f40>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2538020040>",
-        "_build": "<function ActorCriticPolicy._build at 0x7b25380200d0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7b2538020160>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b25380201f0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2538020280>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7b2538020310>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b25380203a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2538020430>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b25380204c0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x79b8f59fc310>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79b8f59fc3a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79b8f59fc430>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79b8f59fc4c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x79b8f59fc550>",
+        "forward": "<function ActorCriticPolicy.forward at 0x79b8f59fc5e0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x79b8f59fc670>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79b8f59fc700>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x79b8f59fc790>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79b8f59fc820>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79b8f59fc8b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x79b8f59fc940>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7b253892b480>"
+        "_abc_impl": "<_abc._abc_data object at 0x79b8f5a00380>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 114688,
+    "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1708635768792101284,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": 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": 1.0,
+    "_current_progress_remaining": -0.1468799999999999,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 33,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dbf41e305d3a0b52e13b973ece0bb28ffca5bcf57636bcf9b68102feec544e
-size 1120
+oid sha256:597aa272904dac1cffbeef30062e38a022ea7bc1fd45259be453d00ec098ce51
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54fdcee2ded687ee5b6afdcf9b5953281d724fe7c9992623feb40a3a88559911
+oid sha256:a75db4ef42c1cd03eb153c5ef64dea2ca84caf0ac55a1e3ec54e348480513b82
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -679.5991593, "std_reward": 267.0955254601165, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-22T20:58:49.180134"}
+{"mean_reward": -214.0649515, "std_reward": 75.06528401857081, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-22T21:05:20.560132"}