trained lunar lander

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 271.18 +/- 19.34
+      value: -460.90 +/- 183.89
       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 0x7cb4453de340>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cb4453de3e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cb4453de480>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cb4453de520>", "_build": "<function ActorCriticPolicy._build at 0x7cb4453de5c0>", "forward": "<function ActorCriticPolicy.forward at 0x7cb4453de660>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cb4453de700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cb4453de7a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7cb4453de840>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cb4453de8e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cb4453de980>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cb4453dea20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cb445362980>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1754743816557167930, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "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 0x7c914d27c180>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c914d27c220>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c914d27c2c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c914d27c360>", "_build": "<function ActorCriticPolicy._build at 0x7c914d27c400>", "forward": "<function ActorCriticPolicy.forward at 0x7c914d27c4a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c914d27c540>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c914d27c5e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c914d27c680>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c914d27c720>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c914d27c7c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c914d27c860>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c914f3bbb40>"}, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "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 sha256:464848bbb0090763ab648dd0593cc270bbfb8e445a0e577333028d2f4d47a205
-size 148132
+oid sha256:0c4cb07beb10503dbc726104653c9f83c25c21f9a19a54bebb534077473cd447
+size 55226

ppo-LunarLander-v2/data

@@ -4,54 +4,42 @@
         ":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 0x7cb4453de340>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cb4453de3e0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cb4453de480>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cb4453de520>",
-        "_build": "<function ActorCriticPolicy._build at 0x7cb4453de5c0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7cb4453de660>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cb4453de700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cb4453de7a0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7cb4453de840>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cb4453de8e0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cb4453de980>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cb4453dea20>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7c914d27c180>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c914d27c220>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c914d27c2c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c914d27c360>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c914d27c400>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c914d27c4a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c914d27c540>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c914d27c5e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c914d27c680>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c914d27c720>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c914d27c7c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c914d27c860>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7cb445362980>"
+        "_abc_impl": "<_abc._abc_data object at 0x7c914f3bbb40>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1754743816557167930,
+    "start_time": 0.0,
     "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
-    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": 1.0,
     "_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,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
     "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 sha256:0347b9d99dee6c859c60555b5d98d49b72274f9e05b1b1ca9a5a3d1256767ef4
-size 88362
+oid sha256:13dbf41e305d3a0b52e13b973ece0bb28ffca5bcf57636bcf9b68102feec544e
+size 1120

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d36572c8441a5da254106f8dc10c30a5957d9f06703b050fada19c165a043f
+oid sha256:cf65296f5e31c2097fa8095538c3795e53f4dca5977831d7a41cc8394752241f
 size 43762

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87094f023879588052a70dbdc2ab651b5d12be00f46199028a34a4ef44515796
-size 171053
+oid sha256:7029098b8bd7b4ae3049aa646a69257ffe3283cd3a6a5f59bb5edc500d7f6c29
+size 185236

results.json

@@ -1 +1 @@
-{"mean_reward": 271.17603429999997, "std_reward": 19.336566458011376, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T13:19:15.183902"}
+{"mean_reward": -460.9001123, "std_reward": 183.89117517712597, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T13:47:22.977297"}