Upload PPO Acrobot-v1 trained agent

Acrobot-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cb10cd7262f14634a60a0c1a22a2ddaa7c666901b3a5b1fded4f9fffd0585d
+oid sha256:685799f562d9d5f7e3f0aa6856e98077965710dbbc2d1b988451fb2d5769a364
 size 147907

Acrobot-v1/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 0x7cc21cf2ed40>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cc21cf2ede0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cc21cf2ee80>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cc21cf2ef20>",
-        "_build": "<function ActorCriticPolicy._build at 0x7cc21cf2efc0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7cc21cf2f060>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cc21cf2f100>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cc21cf2f1a0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7cc21cf2f240>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cc21cf2f2e0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cc21cf2f380>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cc21cf2f420>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f2b14e7f9c0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2b14e7fa60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2b14e7fb00>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2b14e7fba0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f2b14e7fc40>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f2b14e7fce0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2b14e7fd80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2b14e7fe20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f2b14e7fec0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2b14e7ff60>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2b14e8c040>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2b14e8c0e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7cc21d0ad280>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f2b14e6b280>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1762555126076505531,
+    "start_time": 1762557295198285642,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWV9gEAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWgAEAAAAAAADGxS0/qvw7P7ohyL4Aoms/bxpawI5PZr/v7Uc/X+MfP1/1lD4b7XS/wTaCvwxI9L7haGg/w63WPiQaXz/WFvu+44xMQPKzrcA4tGg/VWbVPm6i0T7ajmm/7Gecvz0olT+7iH8/PwB3vemcfj+L59Q9je4LPhgAZrv2HR4/RFVJv7QMHr/QYkk/lT85QOBVFcAr7n8/6xa/vJ0tbT8LscC+VhOav+p4LUDCYeM8wOZ/v/HaYb/4CvE+JIiMPycj0z+3rOI9WW1+PzTafr+ctMG92gHUv+/jX7+wRBU/cfpPPyJ9lz60iXS/uNjiP2qtTMDbXF2+YvJ5P+Mgvz6Bfm2/jnI+QLJVD8AgnXu+xyZ4v1SSNb8jdzQ/5PePvgCbd0AVU3A/8Giwvku4dD8FT5Y+rA+Xv9L5PUBvZWw/YH/EPm4NVz8B4gq/WRA4P8NfIcALAhg/AvxNP4TqHj/2s0i/3esRQLupecAr7uc+Zzpkv7rsLLxa/H8/ihLZPUJiST+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSxBLBoaUjAFDlHSUUpQu"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,13 +45,13 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVxBMAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDBAAAjsKUhpRSlIwBbJRoCWgMjAJpNJSJiIeUUpQoSwNoEE5OTkr/////Sv////9LAHSUYkMESAAAAJSGlFKUjAF0lEdAfhzymALApXV9lChoBmgJaA9DBAAAosKUhpRSlGgVaAloGEMEUgAAAJSGlFKUaB1HQH4c/tpmEoR1fZQoaAZoCWgPQwQAAKTClIaUUpRoFWgJaBhDBFMAAACUhpRSlGgdR0B+HQsrd30PdX2UKGgGaAloD0MEAAD0wpSGlFKUaBVoCWgYQwR7AAAAlIaUUpRoHUdAfh19QoCuEHV9lChoBmgJaA9DBAAAmsKUhpRSlGgVaAloGEMETgAAAJSGlFKUaB1HQH4dqvaDf3x1fZQoaAZoCWgPQwQAAKrClIaUUpRoFWgJaBhDBFYAAACUhpRSlGgdR0B+Hftb9qDcdX2UKGgGaAloD0MEAAC2wpSGlFKUaBVoCWgYQwRcAAAAlIaUUpRoHUdAfh6N0NjLCHV9lChoBmgJaA9DBAAAuMKUhpRSlGgVaAloGEMEXQAAAJSGlFKUaB1HQH4eqSDAaeh1fZQoaAZoCWgPQwQAANzClIaUUpRoFWgJaBhDBG8AAACUhpRSlGgdR0B+HqlnAZbZdX2UKGgGaAloD0MEAAB8wpSGlFKUaBVoCWgYQwRAAAAAlIaUUpRoHUdAfh617pmmL3V9lChoBmgJaA9DBAAAnMKUhpRSlGgVaAloGEMETwAAAJSGlFKUaB1HQH4e2UGFBY51fZQoaAZoCWgPQwQAALrClIaUUpRoFWgJaBhDBF4AAACUhpRSlGgdR0B+IEdlum78dX2UKGgGaAloD0MEAACOwpSGlFKUaBVoCWgYQwRIAAAAlIaUUpRoHUdAfiByqdYnv3V9lChoBmgJaA9DBAAAjMKUhpRSlGgVaAloGEMERwAAAJSGlFKUaB1HQH4ghz7uUll1fZQoaAZoCWgPQwQAAJrClIaUUpRoFWgJaBhDBE4AAACUhpRSlGgdR0B+IJx6v7m/dX2UKGgGaAloD0MEAACOwpSGlFKUaBVoCWgYQwRIAAAAlIaUUpRoHUdAfiDAJb+tKnV9lChoBmgJaA9DBAAAvMKUhpRSlGgVaAloGEMEXwAAAJSGlFKUaB1HQH4hTDwYtQN1fZQoaAZoCWgPQwQAAI7ClIaUUpRoFWgJaBhDBEgAAACUhpRSlGgdR0B+IWO7xusLdX2UKGgGaAloD0MEAACawpSGlFKUaBVoCWgYQwROAAAAlIaUUpRoHUdAfiF6Vt4zJ3V9lChoBmgJaA9DBAAAusKUhpRSlGgVaAloGEMEXgAAAJSGlFKUaB1HQH4hxK6Fuel1fZQoaAZoCWgPQwQAAJzClIaUUpRoFWgJaBhDBE8AAACUhpRSlGgdR0B+IhhsqJ/HdX2UKGgGaAloD0MEAADmwpSGlFKUaBVoCWgYQwR0AAAAlIaUUpRoHUdAfiIwOe8PF3V9lChoBmgJaA9DBAAAmsKUhpRSlGgVaAloGEMETgAAAJSGlFKUaB1HQH4iixeLNwB1fZQoaAZoCWgPQwQAAK7ClIaUUpRoFWgJaBhDBFgAAACUhpRSlGgdR0B+IuXD3ueCdX2UKGgGaAloD0MEAAC0wpSGlFKUaBVoCWgYQwRbAAAAlIaUUpRoHUdAfiMeCkGiYnV9lChoBmgJaA9DBAAAssKUhpRSlGgVaAloGEMEWgAAAJSGlFKUaB1HQH4jQF9roGJ1fZQoaAZoCWgPQwQAAMbClIaUUpRoFWgJaBhDBGQAAACUhpRSlGgdR0B+I4OrhisodX2UKGgGaAloD0MEAAB8wpSGlFKUaBVoCWgYQwRAAAAAlIaUUpRoHUdAfiOO9FnZkHV9lChoBmgJaA9DBAAAosKUhpRSlGgVaAloGEMEUgAAAJSGlFKUaB1HQH4kaUmlZYB1fZQoaAZoCWgPQwQAAKbClIaUUpRoFWgJaBhDBFQAAACUhpRSlGgdR0B+JJsVLzwudX2UKGgGaAloD0MEAAC2wpSGlFKUaBVoCWgYQwRcAAAAlIaUUpRoHUdAfiTiFCb+cnV9lChoBmgJaA9DBAAAkMKUhpRSlGgVaAloGEMESQAAAJSGlFKUaB1HQH4k4oJAt4B1fZQoaAZoCWgPQwQAAJrClIaUUpRoFWgJaBhDBE4AAACUhpRSlGgdR0B+JO+SKWLQdX2UKGgGaAloD0MEAADAwpSGlFKUaBVoCWgYQwRhAAAAlIaUUpRoHUdAfiT9QXQ+lnV9lChoBmgJaA9DBAAAjMKUhpRSlGgVaAloGEMERwAAAJSGlFKUaB1HQH4lCe2/i5x1fZQoaAZoCWgPQwQAAHzClIaUUpRoFWgJaBhDBEAAAACUhpRSlGgdR0B+JSHpKSPmdX2UKGgGaAloD0MEAACewpSGlFKUaBVoCWgYQwRQAAAAlIaUUpRoHUdAfiXFINEw4HV9lChoBmgJaA9DBAAAkMKUhpRSlGgVaAloGEMESQAAAJSGlFKUaB1HQH4mM9Oh0yR1fZQoaAZoCWgPQwQAAIzClIaUUpRoFWgJaBhDBEcAAACUhpRSlGgdR0B+JlsUIsy0dX2UKGgGaAloD0MEAACkwpSGlFKUaBVoCWgYQwRTAAAAlIaUUpRoHUdAfiZbVz6rNnV9lChoBmgJaA9DBAAAqsKUhpRSlGgVaAloGEMEVgAAAJSGlFKUaB1HQH4nJTl1bJR1fZQoaAZoCWgPQwQAAMTClIaUUpRoFWgJaBhDBGMAAACUhpRSlGgdR0B+J/S2H+IedX2UKGgGaAloD0MEAACMwpSGlFKUaBVoCWgYQwRHAAAAlIaUUpRoHUdAfigLNOdoWnV9lChoBmgJaA9DBAAAjMKUhpRSlGgVaAloGEMERwAAAJSGlFKUaB1HQH4oIczZYgd1fZQoaAZoCWgPQwQAAJ7ClIaUUpRoFWgJaBhDBFAAAACUhpRSlGgdR0B+KDqKP4mDdX2UKGgGaAloD0MEAACiwpSGlFKUaBVoCWgYQwRSAAAAlIaUUpRoHUdAfiiLQHAymHV9lChoBmgJaA9DBAAAtMKUhpRSlGgVaAloGEMEWwAAAJSGlFKUaB1HQH4oi4Wk8A91fZQoaAZoCWgPQwQAAOTClIaUUpRoFWgJaBhDBHMAAACUhpRSlGgdR0B+KLpUxVQzdX2UKGgGaAloD0MEAACKwpSGlFKUaBVoCWgYQwRGAAAAlIaUUpRoHUdAfijc45tFa3V9lChoBmgJaA9DBAAAqsKUhpRSlGgVaAloGEMEVgAAAJSGlFKUaB1HQH4o3SjQAuJ1fZQoaAZoCWgPQwQAAKjClIaUUpRoFWgJaBhDBFUAAACUhpRSlGgdR0B+KOh/RVp9dX2UKGgGaAloD0MEAAC6wpSGlFKUaBVoCWgYQwReAAAAlIaUUpRoHUdAfikg5BC2MXV9lChoBmgJaA9DBAAAkMKUhpRSlGgVaAloGEMESQAAAJSGlFKUaB1HQH4ppw0fozN1fZQoaAZoCWgPQwQAAJLClIaUUpRoFWgJaBhDBEoAAACUhpRSlGgdR0B+KbXAdn01dX2UKGgGaAloD0MEAACowpSGlFKUaBVoCWgYQwRVAAAAlIaUUpRoHUdAfioSgoPTX3V9lChoBmgJaA9DBAAARcOUhpRSlGgVaAloGEMExgAAAJSGlFKUaB1HQH4qeby6MBJ1fZQoaAZoCWgPQwQAAI7ClIaUUpRoFWgJaBhDBEgAAACUhpRSlGgdR0B+K1fqoqCpdX2UKGgGaAloD0MEAACawpSGlFKUaBVoCWgYQwROAAAAlIaUUpRoHUdAfiuPTXrdFnV9lChoBmgJaA9DBAAAmsKUhpRSlGgVaAloGEMETgAAAJSGlFKUaB1HQH4sJFkQPI51fZQoaAZoCWgPQwQAAKjClIaUUpRoFWgJaBhDBFUAAACUhpRSlGgdR0B+LCSjgydndX2UKGgGaAloD0MEAACuwpSGlFKUaBVoCWgYQwRYAAAAlIaUUpRoHUdAfiwxy4nWrnV9lChoBmgJaA9DBAAAjMKUhpRSlGgVaAloGEMERwAAAJSGlFKUaB1HQH4sMhxHXmN1fZQoaAZoCWgPQwQAAJrClIaUUpRoFWgJaBhDBE4AAACUhpRSlGgdR0B+LFWbPQfIdX2UKGgGaAloD0MEAACawpSGlFKUaBVoCWgYQwROAAAAlIaUUpRoHUdAfix4C6pYLnV9lChoBmgJaA9DBAAAoMKUhpRSlGgVaAloGEMEUQAAAJSGlFKUaB1HQH4so3irDIl1fZQoaAZoCWgPQwQAAJrClIaUUpRoFWgJaBhDBE4AAACUhpRSlGgdR0B+LM4CIUJwdX2UKGgGaAloD0MEAACKwpSGlFKUaBVoCWgYQwRGAAAAlIaUUpRoHUdAfiznoPkJbHV9lChoBmgJaA9DBAAAusKUhpRSlGgVaAloGEMEXgAAAJSGlFKUaB1HQH4s85XEIgN1fZQoaAZoCWgPQwQAAIzClIaUUpRoFWgJaBhDBEcAAACUhpRSlGgdR0B+LP876pHadX2UKGgGaAloD0MEAACMwpSGlFKUaBVoCWgYQwRHAAAAlIaUUpRoHUdAfi24j8k2P3V9lChoBmgJaA9DBAAApMKUhpRSlGgVaAloGEMEUwAAAJSGlFKUaB1HQH4t2LpA2Q51fZQoaAZoCWgPQwQAACHDlIaUUpRoFWgJaBhDBKIAAACUhpRSlGgdR0B+Lnpkf9xZdX2UKGgGaAloD0MEAACSwpSGlFKUaBVoCWgYQwRKAAAAlIaUUpRoHUdAfi6xCpm29nV9lChoBmgJaA9DBAAAkMKUhpRSlGgVaAloGEMESQAAAJSGlFKUaB1HQH4u1Drqt5l1fZQoaAZoCWgPQwQAAJzClIaUUpRoFWgJaBhDBE8AAACUhpRSlGgdR0B+L6AEt/WldX2UKGgGaAloD0MEAACgwpSGlFKUaBVoCWgYQwRRAAAAlIaUUpRoHUdAfjAJmdy1eHV9lChoBmgJaA9DBAAAjsKUhpRSlGgVaAloGEMESAAAAJSGlFKUaB1HQH4wFd5Y5kt1fZQoaAZoCWgPQwQAAJrClIaUUpRoFWgJaBhDBE4AAACUhpRSlGgdR0B+MC1y/9HddX2UKGgGaAloD0MEAACywpSGlFKUaBVoCWgYQwRaAAAAlIaUUpRoHUdAfjAtuDSPVHV9lChoBmgJaA9DBAAAnMKUhpRSlGgVaAloGEMETwAAAJSGlFKUaB1HQH4wUNayKN11fZQoaAZoCWgPQwQAAMDClIaUUpRoFWgJaBhDBGEAAACUhpRSlGgdR0B+MH3rUsnRdX2UKGgGaAloD0MEAACkwpSGlFKUaBVoCWgYQwRTAAAAlIaUUpRoHUdAfjCJuVHFxXV9lChoBmgJaA9DBAAAuMKUhpRSlGgVaAloGEMEXQAAAJSGlFKUaB1HQH4wt9H+ZPV1fZQoaAZoCWgPQwQAAJ7ClIaUUpRoFWgJaBhDBFAAAACUhpRSlGgdR0B+MZgQYk3TdX2UKGgGaAloD0MEAACAwpSGlFKUaBVoCWgYQwRBAAAAlIaUUpRoHUdAfjGYXfqHGnV9lChoBmgJaA9DBAAAjMKUhpRSlGgVaAloGEMERwAAAJSGlFKUaB1HQH4yFmz0HyF1fZQoaAZoCWgPQwQAAArDlIaUUpRoFWgJaBhDBIsAAACUhpRSlGgdR0B+MpFz+3pfdX2UKGgGaAloD0MEAACewpSGlFKUaBVoCWgYQwRQAAAAlIaUUpRoHUdAfjKdBBzFM3V9lChoBmgJaA9DBAAAmsKUhpRSlGgVaAloGEMETgAAAJSGlFKUaB1HQH4zV4xDb8F1fZQoaAZoCWgPQwQAAJ7ClIaUUpRoFWgJaBhDBFAAAACUhpRSlGgdR0B+M91klNUPdX2UKGgGaAloD0MEAACUwpSGlFKUaBVoCWgYQwRLAAAAlIaUUpRoHUdAfjPduHerMnV9lChoBmgJaA9DBAAAjsKUhpRSlGgVaAloGEMESAAAAJSGlFKUaB1HQH4z6QaJhv11fZQoaAZoCWgPQwQAACjDlIaUUpRoFWgJaBhDBKkAAACUhpRSlGgdR0B+NAqFyq+8dX2UKGgGaAloD0MEAACowpSGlFKUaBVoCWgYQwRVAAAAlIaUUpRoHUdAfjQK2KEWZnV9lChoBmgJaA9DBAAApMKUhpRSlGgVaAloGEMEUwAAAJSGlFKUaB1HQH40FhLGrCF1fZQoaAZoCWgPQwQAAKjClIaUUpRoFWgJaBhDBFUAAACUhpRSlGgdR0B+NCw0O3DvdX2UKGgGaAloD0MEAACawpSGlFKUaBVoCWgYQwROAAAAlIaUUpRoHUdAfjQ3VCojwHV9lChoBmgJaA9DBAAAGMOUhpRSlGgVaAloGEMEmQAAAJSGlFKUaB1HQH40o+bExZd1fZQoaAZoCWgPQwQAAIzClIaUUpRoFWgJaBhDBEcAAACUhpRSlGgdR0B+NK9du5z6dX2UKGgGaAloD0MEAACQwpSGlFKUaBVoCWgYQwRJAAAAlIaUUpRoHUdAfjTFWXC0nnVlLg=="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 248,
+    "_n_updates": 252,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -89,14 +89,14 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
         "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function RolloutBuffer.__init__ at 0x7cc21d097b00>",
-        "reset": "<function RolloutBuffer.reset at 0x7cc21d097ba0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7cc21d097c40>",
-        "add": "<function RolloutBuffer.add at 0x7cc21d097d80>",
-        "get": "<function RolloutBuffer.get at 0x7cc21d097e20>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7cc21d097ec0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7f2b14e00860>",
+        "reset": "<function RolloutBuffer.reset at 0x7f2b14e00900>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f2b14e009a0>",
+        "add": "<function RolloutBuffer.add at 0x7f2b14e00ae0>",
+        "get": "<function RolloutBuffer.get at 0x7f2b14e00b80>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f2b14e00c20>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7cc21d1e1680>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f2b14f9b5c0>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

Acrobot-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d40d98cccce0bcbba327612fb747711a7b486bfa0a47bcd6ff31c160c8d8e4
+oid sha256:37baf8e221f391c3edb273f1a76a90d583c0ff1b1a531c9a4a621617efc92bd5
 size 85815

Acrobot-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c3ef81d92cf91b4bb9ec1d68b5193e0c23a3127e17c1a9d8ff4ead5a16df76
+oid sha256:025b15fce49009d647dd3ad3b4dfbfc0b96f43e84ecd6fe188e1d8f1d95ad8c9
 size 42687

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Acrobot-v1
     metrics:
     - type: mean_reward
-      value: -80.70 +/- 6.28
+      value: -80.20 +/- 3.94
       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 0x7cc21cf2ed40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cc21cf2ede0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cc21cf2ee80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cc21cf2ef20>", "_build": "<function ActorCriticPolicy._build at 0x7cc21cf2efc0>", "forward": "<function ActorCriticPolicy.forward at 0x7cc21cf2f060>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cc21cf2f100>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cc21cf2f1a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7cc21cf2f240>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cc21cf2f2e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cc21cf2f380>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cc21cf2f420>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cc21d0ad280>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1762555126076505531, "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", "_shape": [6], "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "bounded_below": "[ True  True  True  True  True  True]", "high": "[ 1.        1.        1.        1.       12.566371 28.274334]", "bounded_above": "[ True  True  True  True  True  True]", "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgDAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "3", "start": "0", "_shape": [], "_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, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7cc21d097b00>", "reset": "<function RolloutBuffer.reset at 0x7cc21d097ba0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7cc21d097c40>", "add": "<function RolloutBuffer.add at 0x7cc21d097d80>", "get": "<function RolloutBuffer.get at 0x7cc21d097e20>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7cc21d097ec0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cc21d1e1680>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2", "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 0x7f2b14e7f9c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2b14e7fa60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2b14e7fb00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2b14e7fba0>", "_build": "<function ActorCriticPolicy._build at 0x7f2b14e7fc40>", "forward": "<function ActorCriticPolicy.forward at 0x7f2b14e7fce0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2b14e7fd80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2b14e7fe20>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2b14e7fec0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2b14e7ff60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2b14e8c040>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2b14e8c0e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f2b14e6b280>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1762557295198285642, "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": 252, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [6], "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "bounded_below": "[ True  True  True  True  True  True]", "high": "[ 1.        1.        1.        1.       12.566371 28.274334]", "bounded_above": "[ True  True  True  True  True  True]", "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgDAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "3", "start": "0", "_shape": [], "_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, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7f2b14e00860>", "reset": "<function RolloutBuffer.reset at 0x7f2b14e00900>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f2b14e009a0>", "add": "<function RolloutBuffer.add at 0x7f2b14e00ae0>", "get": "<function RolloutBuffer.get at 0x7f2b14e00b80>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f2b14e00c20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f2b14f9b5c0>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2", "OpenAI Gym": "0.25.2"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112bdb883d7f6b6481d67e60e5b581d18038fb7910c4054c191c4a896207b145
-size 691558
+oid sha256:6f0f7f0d722378f8866202a48fe1de8356a2685bc7984e4cd51214264c0c30e1
+size 696956

results.json

@@ -1 +1 @@
-{"mean_reward": -80.7, "std_reward": 6.277738446287803, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-07T22:55:54.081515"}
+{"mean_reward": -80.2, "std_reward": 3.944616584663204, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-07T23:26:56.290813"}