A new tochomodel with 5000000 steps try III

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 240.27 +/- 39.23
+      value: 272.67 +/- 24.84
       name: mean_reward
     task:
       type: reinforcement-learning

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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7ff61e6bbee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff61e6bbf70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff61e640040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff61e6400d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff61e640160>", "forward": "<function ActorCriticPolicy.forward at 0x7ff61e6401f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff61e640280>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff61e640310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff61e6403a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff61e640430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff61e6404c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff61e63d150>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652205041.363578, "learning_rate": 0.0003, "tensorboard_log": "models/logs", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVYxAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMInBa86Cu3Y0CUhpRSlIwBbJRN6AOMAXSUR0C3MEB9b5dodX2UKGgGaAloD0MII9xkVJl9ZECUhpRSlGgVTegDaBZHQLcwjwS8J2N1fZQoaAZoCWgPQwjjqNxELUhnQJSGlFKUaBVN6ANoFkdAtzCr9S/CZXV9lChoBmgJaA9DCBSVDWsqcmtAlIaUUpRoFUvbaBZHQLc07NVinYR1fZQoaAZoCWgPQwi9pgcFpbpXQJSGlFKUaBVN6ANoFkdAtzVExZdOZnV9lChoBmgJaA9DCEusjEY+PV9AlIaUUpRoFU3oA2gWR0C3NUa6reZYdX2UKGgGaAloD0MI4KKTpdZVbkCUhpRSlGgVTWQBaBZHQLc4UgEEC/51fZQoaAZoCWgPQwjnpzgOPFZhQJSGlFKUaBVN6ANoFkdAtzhnDKoybnV9lChoBmgJaA9DCEJ3SZyVG2pAlIaUUpRoFUv0aBZHQLc5I4dIXj51fZQoaAZoCWgPQwii0/NuLDBiQJSGlFKUaBVN6ANoFkdAtzlt57gKnnV9lChoBmgJaA9DCBCugEK9hGtAlIaUUpRoFU0eAWgWR0C3OYMDGLk0dX2UKGgGaAloD0MIo66196nPWECUhpRSlGgVTegDaBZHQLc5u1baAWl1fZQoaAZoCWgPQwg+zF62HbpgQJSGlFKUaBVN6ANoFkdAtzoLposZpHV9lChoBmgJaA9DCPYKC+4H02hAlIaUUpRoFU3oA2gWR0C3OqHg5zYFdX2UKGgGaAloD0MIRDF5A8x8NsCUhpRSlGgVS4JoFkdAtzr7hNucc3V9lChoBmgJaA9DCPDeUWNCaGFAlIaUUpRoFU3oA2gWR0C3PGMNDtw8dX2UKGgGaAloD0MI1CgkmVWZakCUhpRSlGgVTXQCaBZHQLc8ZyNn5BV1fZQoaAZoCWgPQwjghhiv+WdiQJSGlFKUaBVN6ANoFkdAtzzcrhBJI3V9lChoBmgJaA9DCNHoDmLn5W1AlIaUUpRoFUvuaBZHQLc9Akadc0N1fZQoaAZoCWgPQwikiXeAp6ZnQJSGlFKUaBVL6mgWR0C3Pd8wlByCdX2UKGgGaAloD0MIzEBl/HvraECUhpRSlGgVS/poFkdAtz58NZvDQHV9lChoBmgJaA9DCJ8ENudgEWZAlIaUUpRoFU3oA2gWR0C3PqGU8mrsdX2UKGgGaAloD0MIvi7Df7pwZkCUhpRSlGgVTegDaBZHQLc/J/PgNw11fZQoaAZoCWgPQwg1fAvrxj5qQJSGlFKUaBVL9WgWR0C3P9T101ZUdX2UKGgGaAloD0MIrg0V4/zDXUCUhpRSlGgVTegDaBZHQLdAb2pyZKF1fZQoaAZoCWgPQwixNVt5yYhdQJSGlFKUaBVN6ANoFkdAt0FCXTmW+3V9lChoBmgJaA9DCFtEFJM3PkBAlIaUUpRoFUuhaBZHQLdBaltCRfZ1fZQoaAZoCWgPQwj2DUxulPxrQJSGlFKUaBVL1mgWR0C3Q573Cbc5dX2UKGgGaAloD0MIm6vmOaLMY0CUhpRSlGgVTegDaBZHQLdED5Rjz7N1fZQoaAZoCWgPQwhB8zl3O4RqQJSGlFKUaBVL/2gWR0C3RXNdAxBWdX2UKGgGaAloD0MILsvXZfhjOsCUhpRSlGgVS5FoFkdAt0ZwhStNjHV9lChoBmgJaA9DCEJD/wQX1WFAlIaUUpRoFU3oA2gWR0C3R0rT2FnJdX2UKGgGaAloD0MIycwFLg/iY0CUhpRSlGgVTegDaBZHQLdHXo371qZ1fZQoaAZoCWgPQwi31EFeD3paQJSGlFKUaBVN6ANoFkdAt0hXH2h7FHV9lChoBmgJaA9DCDJ2wktw411AlIaUUpRoFU3oA2gWR0C3SGvcSGrTdX2UKGgGaAloD0MIRZ4kXTMxZ0CUhpRSlGgVTegDaBZHQLdI8cGC7K91fZQoaAZoCWgPQwgR/dr66ZpqQJSGlFKUaBVNBAFoFkdAt0mBBX0Xg3V9lChoBmgJaA9DCDJZ3H/kompAlIaUUpRoFUv4aBZHQLdKLoUzsQd1fZQoaAZoCWgPQwjyXUpdMgdvQJSGlFKUaBVL62gWR0C3Sq2bsniOdX2UKGgGaAloD0MIwvuqXKivW0CUhpRSlGgVTegDaBZHQLdLTfaYeDF1fZQoaAZoCWgPQwid2a7Qh2liQJSGlFKUaBVN6ANoFkdAt0vK6y0KJHV9lChoBmgJaA9DCPUQje4gvFxAlIaUUpRoFU3oA2gWR0C3S/Ow5eZ5dX2UKGgGaAloD0MIApoIGx5Ma0CUhpRSlGgVS95oFkdAt0wJvBJqZnV9lChoBmgJaA9DCH6qCg3Ep1NAlIaUUpRoFUucaBZHQLdMUtOEdvN1fZQoaAZoCWgPQwiN0xBVeENgQJSGlFKUaBVN6ANoFkdAt0y9BIFvAHV9lChoBmgJaA9DCCMw1jcwWmFAlIaUUpRoFU3oA2gWR0C3TUOUliSadX2UKGgGaAloD0MIY35uaMqOP0CUhpRSlGgVS3poFkdAt01WPT5O8HV9lChoBmgJaA9DCGAGY0QiuGRAlIaUUpRoFU3oA2gWR0C3TWK9kBjndX2UKGgGaAloD0MIBtUGJ6IZaECUhpRSlGgVTegDaBZHQLdOXnJ1aGJ1fZQoaAZoCWgPQwhWSWQfZI06QJSGlFKUaBVLoWgWR0C3TznmRvFWdX2UKGgGaAloD0MIDI/9LBbfbECUhpRSlGgVS/hoFkdAt09mBg/kenV9lChoBmgJaA9DCOi7W1mi70HAlIaUUpRoFUu3aBZHQLdPmuk1uR91fZQoaAZoCWgPQwik4v+OqNNnQJSGlFKUaBVN6ANoFkdAt0+wJ9iMHnV9lChoBmgJaA9DCIGWrmCbdGtAlIaUUpRoFUvxaBZHQLdPu+ueSSx1fZQoaAZoCWgPQwjIs8u3PiwawJSGlFKUaBVLhWgWR0C3UV1pCa7VdX2UKGgGaAloD0MIoWRyameBYECUhpRSlGgVTegDaBZHQLdRrKYAsCl1fZQoaAZoCWgPQwg4EmiwKZluQJSGlFKUaBVNDwFoFkdAt1Himbb1y3V9lChoBmgJaA9DCCjU00fgVGZAlIaUUpRoFU0nAWgWR0C3VcbSmZVodX2UKGgGaAloD0MId6OP+QBRa0CUhpRSlGgVTSwBaBZHQLdWGwkgOjJ1fZQoaAZoCWgPQwjON6J7VtFhQJSGlFKUaBVN6ANoFkdAt1d9lSS/03V9lChoBmgJaA9DCI9TdCSX4GtAlIaUUpRoFU0IAWgWR0C3WCqHKwIMdX2UKGgGaAloD0MIDJOpglGHRkCUhpRSlGgVS5doFkdAt1hAm4RVZXV9lChoBmgJaA9DCAbYR6euO2NAlIaUUpRoFU3oA2gWR0C3WInnlnyvdX2UKGgGaAloD0MICp+tgwOOYUCUhpRSlGgVTegDaBZHQLdYnkyk9EF1fZQoaAZoCWgPQwiuga0SrIBpQJSGlFKUaBVNKgNoFkdAt1jbAXVLBnV9lChoBmgJaA9DCD1+b9Mf52VAlIaUUpRoFU3oA2gWR0C3WaXQD3dsdX2UKGgGaAloD0MIpMfvbfrrIUCUhpRSlGgVS6VoFkdAt1pVa4c3l3V9lChoBmgJaA9DCMu5FFeVRSVAlIaUUpRoFUt4aBZHQLdaWAB1cMV1fZQoaAZoCWgPQwh+chQgim1jQJSGlFKUaBVN6ANoFkdAt1qoZTAFgXV9lChoBmgJaA9DCFHB4QWRjm5AlIaUUpRoFU0SAWgWR0C3W8yCz1K5dX2UKGgGaAloD0MI0jjU70IOZUCUhpRSlGgVTegDaBZHQLdb0yquKXR1fZQoaAZoCWgPQwgG2bJ8XatgQJSGlFKUaBVN6ANoFkdAt1vo41gpjXV9lChoBmgJaA9DCDfjNESViWFAlIaUUpRoFU3oA2gWR0C3XVEPlMh6dX2UKGgGaAloD0MIxF4oYLt0a0CUhpRSlGgVTQgBaBZHQLdd1ZmI0qJ1fZQoaAZoCWgPQwiVnBN7aCBlQJSGlFKUaBVN6ANoFkdAt1/TQY1pCnV9lChoBmgJaA9DCOay0Tm/GGJAlIaUUpRoFU3oA2gWR0C3YHDziCJ5dX2UKGgGaAloD0MIYCAIkKFAZECUhpRSlGgVTegDaBZHQLditnO0LMN1fZQoaAZoCWgPQwjVeOkmMZBcQJSGlFKUaBVN6ANoFkdAt2NY0TDfnHV9lChoBmgJaA9DCFWjVwOUvmRAlIaUUpRoFU3oA2gWR0C3ZaMsQNCrdX2UKGgGaAloD0MIk+NO6WC9PkCUhpRSlGgVS6JoFkdAt2Wqr4nF53V9lChoBmgJaA9DCJtXdVaLJGJAlIaUUpRoFU3oA2gWR0C3Z0ydJ8OTdX2UKGgGaAloD0MIwR9+/ntrVkCUhpRSlGgVTegDaBZHQLdoc2R7qpt1fZQoaAZoCWgPQwj5akdxjoNjQJSGlFKUaBVN6ANoFkdAt2iLy3CsO3V9lChoBmgJaA9DCOqScYxkk1xAlIaUUpRoFU3oA2gWR0C3afG/ag27dX2UKGgGaAloD0MI19mQf2YObUCUhpRSlGgVS/RoFkdAt2okgq3EynV9lChoBmgJaA9DCFRvDWwVbmBAlIaUUpRoFU3oA2gWR0C3auyhnJ1adX2UKGgGaAloD0MInG7ZIf4YW0CUhpRSlGgVTegDaBZHQLdrVYDTz/Z1fZQoaAZoCWgPQwi7Qh8s4yhhQJSGlFKUaBVN6ANoFkdAt2y4pSaVlnV9lChoBmgJaA9DCEp7gy9MGl9AlIaUUpRoFU3oA2gWR0C3bMETxoZidX2UKGgGaAloD0MIbVM8LiriYUCUhpRSlGgVTegDaBZHQLds2/LTx5N1fZQoaAZoCWgPQwiqDrkZbkxeQJSGlFKUaBVN6ANoFkdAt258Aq/dqXV9lChoBmgJaA9DCGFrtvISzW1AlIaUUpRoFUv5aBZHQLduwxD9fkZ1fZQoaAZoCWgPQwg2PL1SlmReQJSGlFKUaBVN6ANoFkdAt28AzGgi/3V9lChoBmgJaA9DCJKwbycRWW1AlIaUUpRoFU2dAWgWR0C3cGZs41gqdX2UKGgGaAloD0MIu2QcI1l5Y0CUhpRSlGgVTegDaBZHQLdw1dQO4G51fZQoaAZoCWgPQwiZnNoZJthmQJSGlFKUaBVN6ANoFkdAt3FuEpRXOnV9lChoBmgJaA9DCGhYjLrWcG9AlIaUUpRoFUvXaBZHQLdxz2Rq46R1fZQoaAZoCWgPQwi/DpwzonT8v5SGlFKUaBVLrWgWR0C3cxiQT238dX2UKGgGaAloD0MIXmOXqN7gX0CUhpRSlGgVTegDaBZHQLd0Dj4YaYN1fZQoaAZoCWgPQwiKk/sdithUQJSGlFKUaBVLqWgWR0C3dBw9vCMxdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "n_steps": 2048, "gamma": 0.9999, "gae_lambda": 0.97, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.29 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "False", "Numpy": "1.21.6", "Gym": "0.21.0"}}
+{"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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7ff7a1866ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff7a1866f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff7a17eb040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff7a17eb0d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff7a17eb160>", "forward": "<function ActorCriticPolicy.forward at 0x7ff7a17eb1f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff7a17eb280>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff7a17eb310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff7a17eb3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff7a17eb430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff7a17eb4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff7a17e8150>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652188435.1278176, "learning_rate": 0.0003, "tensorboard_log": "models/logs", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVAQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGgvaG9tZS92Z29uaS92Z29uaXNhbnovZ2l0L2RybHRmLy50b3gvZHJsdGYvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMaC9ob21lL3Znb25pL3Znb25pc2Fuei9naXQvZHJsdGYvLnRveC9kcmx0Zi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_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": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "n_steps": 2048, "gamma": 0.9999, "gae_lambda": 0.97, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.29 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "False", "Numpy": "1.21.6", "Gym": "0.21.0"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a74e2340e48ab7783141a95066fd0872ccc869f6e7c8e44bdd60c1823dbf24b
-size 154918
+oid sha256:83879b1458ba9cc8eaac01cb2d4aa575cd78f5e2c00149c460ed443d579df62d
+size 183905

results.json

@@ -1 +1 @@
-{"mean_reward": 240.26988485074511, "std_reward": 39.22582103647084, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T21:38:52.669362"}
+{"mean_reward": 272.6695799311336, "std_reward": 24.844293035909516, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T21:40:54.760007"}

tocho1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15dff49cd09fc522b30772c1849e0317c5c81ae7102c1f9858c57acc89ebddf3
-size 143824
+oid sha256:613a0fb22ba054d87c9c59129b83affc503f2367f1cb0abe33b2343baab5e70c
+size 143833

tocho1/data

@@ -4,19 +4,19 @@
         ":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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7feac2f37c10>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7feac2f37ca0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7feac2f37d30>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7feac2f37dc0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7feac2f37e50>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7feac2f37ee0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7feac2f37f70>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7feac2f3a040>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7feac2f3a0d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7feac2f3a160>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7feac2f3a1f0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ff7a1866ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff7a1866f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff7a17eb040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff7a17eb0d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ff7a17eb160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ff7a17eb1f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff7a17eb280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ff7a17eb310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff7a17eb3a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff7a17eb430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff7a17eb4c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7feac2f34840>"
+        "_abc_impl": "<_abc_data object at 0x7ff7a17e8150>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -49,7 +49,7 @@
     "action_noise": null,
     "start_time": 1652188435.1278176,
     "learning_rate": 0.0003,
-    "tensorboard_log": null,
+    "tensorboard_log": "models/logs",
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"