This is another Reinforsement Learning model I made via HuggingFace's course
Browse files- BipedalWalker-v3.zip +2 -2
- BipedalWalker-v3/data +22 -22
- BipedalWalker-v3/policy.optimizer.pth +1 -1
- BipedalWalker-v3/policy.pth +1 -1
- README.md +1 -1
- config.json +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
BipedalWalker-v3.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26b48a45395b4fe77f93f3f49d7eacdd8763a237c40c87295edab5a781ac7b93
|
| 3 |
+
size 181776
|
BipedalWalker-v3/data
CHANGED
|
@@ -4,26 +4,26 @@
|
|
| 4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
| 5 |
"__module__": "stable_baselines3.common.policies",
|
| 6 |
"__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 ",
|
| 7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
| 8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
| 9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
| 10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
| 11 |
-
"_build": "<function ActorCriticPolicy._build at
|
| 12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
| 13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
| 14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
| 15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
| 16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
| 17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
| 18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
| 19 |
"__abstractmethods__": "frozenset()",
|
| 20 |
-
"_abc_impl": "<_abc_data object at
|
| 21 |
},
|
| 22 |
"verbose": false,
|
| 23 |
"policy_kwargs": {},
|
| 24 |
"observation_space": {
|
| 25 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 26 |
-
":serialized:": "
|
| 27 |
"dtype": "float32",
|
| 28 |
"_shape": [
|
| 29 |
24
|
|
@@ -36,7 +36,7 @@
|
|
| 36 |
},
|
| 37 |
"action_space": {
|
| 38 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 39 |
-
":serialized:": "
|
| 40 |
"dtype": "float32",
|
| 41 |
"_shape": [
|
| 42 |
4
|
|
@@ -48,12 +48,12 @@
|
|
| 48 |
"_np_random": null
|
| 49 |
},
|
| 50 |
"n_envs": 64,
|
| 51 |
-
"num_timesteps":
|
| 52 |
-
"_total_timesteps":
|
| 53 |
"_num_timesteps_at_start": 0,
|
| 54 |
"seed": null,
|
| 55 |
"action_noise": null,
|
| 56 |
-
"start_time":
|
| 57 |
"learning_rate": 0.0001,
|
| 58 |
"tensorboard_log": null,
|
| 59 |
"lr_schedule": {
|
|
@@ -62,7 +62,7 @@
|
|
| 62 |
},
|
| 63 |
"_last_obs": {
|
| 64 |
":type:": "<class 'numpy.ndarray'>",
|
| 65 |
-
":serialized:": "
|
| 66 |
},
|
| 67 |
"_last_episode_starts": {
|
| 68 |
":type:": "<class 'numpy.ndarray'>",
|
|
@@ -72,16 +72,16 @@
|
|
| 72 |
"_episode_num": 0,
|
| 73 |
"use_sde": false,
|
| 74 |
"sde_sample_freq": -1,
|
| 75 |
-
"_current_progress_remaining": -
|
| 76 |
"ep_info_buffer": {
|
| 77 |
":type:": "<class 'collections.deque'>",
|
| 78 |
-
":serialized:": "
|
| 79 |
},
|
| 80 |
"ep_success_buffer": {
|
| 81 |
":type:": "<class 'collections.deque'>",
|
| 82 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 83 |
},
|
| 84 |
-
"_n_updates":
|
| 85 |
"n_steps": 1024,
|
| 86 |
"gamma": 0.999,
|
| 87 |
"gae_lambda": 0.96,
|
|
|
|
| 4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
| 5 |
"__module__": "stable_baselines3.common.policies",
|
| 6 |
"__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 ",
|
| 7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fcc14f4ad30>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc14f4adc0>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc14f4ae50>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc14f4aee0>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fcc14f4af70>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fcc14f4e040>",
|
| 13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcc14f4e0d0>",
|
| 14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc14f4e160>",
|
| 15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fcc14f4e1f0>",
|
| 16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc14f4e280>",
|
| 17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc14f4e310>",
|
| 18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc14f4e3a0>",
|
| 19 |
"__abstractmethods__": "frozenset()",
|
| 20 |
+
"_abc_impl": "<_abc_data object at 0x7fcc14f458a0>"
|
| 21 |
},
|
| 22 |
"verbose": false,
|
| 23 |
"policy_kwargs": {},
|
| 24 |
"observation_space": {
|
| 25 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 26 |
+
":serialized:": "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",
|
| 27 |
"dtype": "float32",
|
| 28 |
"_shape": [
|
| 29 |
24
|
|
|
|
| 36 |
},
|
| 37 |
"action_space": {
|
| 38 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 39 |
+
":serialized:": "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",
|
| 40 |
"dtype": "float32",
|
| 41 |
"_shape": [
|
| 42 |
4
|
|
|
|
| 48 |
"_np_random": null
|
| 49 |
},
|
| 50 |
"n_envs": 64,
|
| 51 |
+
"num_timesteps": 10027008,
|
| 52 |
+
"_total_timesteps": 10000000,
|
| 53 |
"_num_timesteps_at_start": 0,
|
| 54 |
"seed": null,
|
| 55 |
"action_noise": null,
|
| 56 |
+
"start_time": 1677207370498747542,
|
| 57 |
"learning_rate": 0.0001,
|
| 58 |
"tensorboard_log": null,
|
| 59 |
"lr_schedule": {
|
|
|
|
| 62 |
},
|
| 63 |
"_last_obs": {
|
| 64 |
":type:": "<class 'numpy.ndarray'>",
|
| 65 |
+
":serialized:": "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"
|
| 66 |
},
|
| 67 |
"_last_episode_starts": {
|
| 68 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
|
| 72 |
"_episode_num": 0,
|
| 73 |
"use_sde": false,
|
| 74 |
"sde_sample_freq": -1,
|
| 75 |
+
"_current_progress_remaining": -0.0027007999999999477,
|
| 76 |
"ep_info_buffer": {
|
| 77 |
":type:": "<class 'collections.deque'>",
|
| 78 |
+
":serialized:": "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"
|
| 79 |
},
|
| 80 |
"ep_success_buffer": {
|
| 81 |
":type:": "<class 'collections.deque'>",
|
| 82 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 83 |
},
|
| 84 |
+
"_n_updates": 1224,
|
| 85 |
"n_steps": 1024,
|
| 86 |
"gamma": 0.999,
|
| 87 |
"gae_lambda": 0.96,
|
BipedalWalker-v3/policy.optimizer.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 105008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a03935c54faa35ba3d06a2e04a843e22e2970deb51b1b4654f8e3bcb02ff41c
|
| 3 |
size 105008
|
BipedalWalker-v3/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51902
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba299718b7702aefde9b3cc70758d3f41150fe841350a14874177eac2178c0cb
|
| 3 |
size 51902
|
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
type: BipedalWalker-v3
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value:
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 16 |
type: BipedalWalker-v3
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: 301.60 +/- 34.36
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
config.json
CHANGED
|
@@ -1 +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 0x7f4418a31310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4418a313a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4418a31430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4418a314c0>", "_build": "<function ActorCriticPolicy._build at 0x7f4418a31550>", "forward": "<function ActorCriticPolicy.forward at 0x7f4418a315e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4418a31670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4418a31700>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4418a31790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4418a31820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4418a318b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4418a31940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f4418a28d80>"}, "verbose": false, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [24], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_np_random": null}, "n_envs": 64, "num_timesteps": 65536, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677206739598268315, "learning_rate": 0.0001, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdRgAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAGAAAAAAAAHI4oz1cNsC7N1SaPO5cAbz4elK/kKEiO5DA1b4nNYC/AACAP0OakD8AFMy40lxvP0CRjroAAAAAD5hfPhsiYj4fDGo+fVB4PtZ0hz4Hy5g+x9mzPnuv4D5mQxo/1S1/P3D5xz7KcIY9zo+SvLpEZr0fuVG/AAAAMzCbyL31/3+/AAAAAJDSgT8CAIC/gNvpvhQ+Mj8AAIA/N9SOPnVzkD6ngZU+vZ6ePj0OrT5bNMM+zMXlPraGDz9E/0M/AACAPwOmzj4NKw88Kx0mvb1c9TsCp4M/YDP4PR5Xwj4BAIC/AAAAABGNQ7/UsDc/tEbyvklwnD8AAIA/0zGJPrDAij7Um48+4FyYPpk6pj4Kgbs+Y7XcPkfdCT/qTj0/AACAP0nv9z227HA83GatvMCsvDxbElS/4CQyO1QyNT6XYIC9AACAP8n3hj/udlW/7MBwP9P9fz8AAIA/y3lnPsEaaj4wTHI+p4iAPjU7jD7ZLZ4+xTC6PhGb6D7LaR8/AACAP3VgFz6YdYY94J8rPK/7ijqyFog/1Y9kv3zZdj///38/AAAAAEmaO78hyA6/QPb7vv//f78AAIA/PP+CPhR8hD4QH4k+4HqRPj24nj6lCLM+AL3SPvGiAz+owTQ/AACAP27B9j2Mvfa8GSOOPZT3rrzo8o8/AIxWu2qEej/sIVY/AACAP5jOVb8AsN84IFPjvYU5gD8AAIA/C350PthEdz467H8++8KHPu8dlD7xEqc+G6nEPpWv9T5+rig/AACAP0kiqD1tLIU7HA/ePIo1wzuVvFW/AABnNWDUA7/5/38/AAAAAKUskD8AACiz3qVqP1UVZrYAAIA/b69gPqc8Yz6PMGs+wIZ5PhYeiD7wiZk+f7q0PjnI4T4lBBs/Typ5P5K5mz2sJCg9X4z5PLp6V71E30i/9v9/vxA+lb79/3+/AAAAAKhEkT8AAAAASlZvP6uqqrMAAAAAzw5xPqDLcz7jU3w+w9qFPkgJkj4euqQ+4uXBPg888j7iTyY/j0l9P/L4xD1taCw9pFV9O228lrwcEUS/2/ilvjChBr4AAIC/AAAAAE96iT+SbEC/iPRwPwAAgD8AAIA//69vPtRocj6s5Ho+9heFPsE0kT5jyqM+tMvAPojb8D7ZXSU/AACAP0K4PT98VuW8SX0SPVrxSDyrRJE/AAAAM5xjIr8AAAAAAAAAAIS8Vb8AAAAAHHb1vtu1+z0AAAAAqG2QPowRkj48Lpc+cmWgPlT+rj7xY8U+eljoPiYiET8rSkc/AACAPzEWbD6zxye8BvsSvU0KYbsKuYs/DwCAP9ApUT///3+/AAAAAIqgVb8AAACz2Ir+vvX/fz8AAAAAsWWAPvragT5nZoY+wJeOPtmRmz4Me68+U47OPicGAT/+pjc/AACAP+Sfpz9wBwS7iwbDvHfkAz3hMU6/TG2LPRj9HL+g8R09AACAP7NvRL4JZbe/iJ4QvkOVlz8AAIA/6lyePlEpoD5FxKU+Gd+vPoXgvz5Rb9g+N8P+PtIiHz90hFo/AACAP1GOuT5kECm9TLP7O3+9jrwJyI8/nLtEPxDrGT/4/X8/AAAAADe0T78AACI20EKZvq0UgD8AAIA/0BSIPnCgiT5+cY4+WiCXPkXhpD6D+7k+4uraPuC+CD+kxTs/AACAP1SbRz76U7c6Bx8dPd9URLwq4ow/AABQMsgFXj/3/3+/AAAAAImCR7/L5hE+SOYQv/z/f78AAAAAdj+BPji3gj5bSoc+mImPPrWZnD6spLA+p+zPPvzgAT/LVzI/AACAP5KBpD1qOJS7ce+8O5+YRDsQ2VW/XBxbvGjhgz0JwoA/AACAP1Bmjz8AfvI5ZGptP3UnzDwAAAAATZtgPkooYz58G2s+ZHB5PuQRiD4ufJk+Tqq0Pv2z4T7yFBs/+lZ5P5okwz7UXkE86t+hvGn6+7wUvVW/AABgMyy3Hr/8/3+/AAAAALYVQz8DAIC/fjRdP6ebgD8AAAAAKmOCPjzegz6ye4g+jM2QPiT7nT5YM7I+7cHRPhwGAz9N6jM/AACAP106JD72++g8OmyEPFOPUj2Pgk+/APPyOjCdYz0ow38/AACAP2NcjT8AsHu4wrEyP2s1w74AAIA/HdNwPkGPcz5mFXw+nbmFPh7lkT5TkaQ+3rXBPhIA8j6zJiY/AACAPztP3D1OEqs8JItLuxKv4zzKvFW/AAA9thiVyr4WAIA/AAAAAKVEkT8AAOAzovZVP4Uufr4AAIA/ke5iPlGCZT6Uim0+eAV8PoJ6iT70Eps+HYm2PikK5D7xkBw/JLZ4PxITzz2ieQS9XGrRO668ubym5lO/bQMyPsA1U739/38/AAAAAJo4iz/cWXg/NFFXPwAAgL8AAAAAR/l0PnvBdz6cNoA+aQeIPpdolD4nZ6c+PAzFPmsr9j5MHyg/AACAP+DfsT63X/a84yKdPIUIsrwgOYo/pEYNP0wfSD8lAIA/AAAAAPUtS7/wkq68/D7PvkdcPj8AAIA/Tt2GPmRliD5rK40+aMaVPtZnoz7GUbg+wPXYPtmFBz/OFzo/AACAPyhjQT580189kJKWvcbCgj1UY1W/AECfNxBP6L6dAIC/AACAP1qijj8AAFi1qfQhP9UDKL8AAIA/hfNsPmakbz5zB3g+AJODPmWMjz6366E+RJi+PqMb7j6SeiM/AACAP+VeYT2DbZO9QnTBOztOfb18cUq/NZXnPrhBxT3//38/AAAAADN6mT/8/38/EFZvP6uqKrQAAAAAO9hiPrprZT4zc20+qux7PvpsiT6xA5s+Jne2Prfz4z6JgRw/AACAPyy4ij6Ichc7a/DkPO1Orzw5A1a/YOd2upgaZ76jDYA/AACAPwwCjj8AgPQ3CBW+PmvQqb0AAIA/Zbx4PomPez6vLoI+Nh6KPg+wlj5N+ak+7hLIPj3z+T7+mys/AACAP3s2XD56FDU9xSgZvSg4e70L+YU/wH48vApWbz8AAAAAAAAAAIb5UL/8/3+/SFyzvmlTh74AAIA/A+KBPp5bgz6B9Ic+Hj6QPqhenT7VgrE+J/LQPlSEAj8XODM/AACAP8MB1T2Wsy+9aaioPX/0gbzHuY8/AMCHuHIbfD9T9AQ/AACAP8/HVb8AAPc2YL/fPXsENz4AAIA/2bh0PlGAdz7kFIA+o+OHPo9BlD4gO6c+aNjEPq3q9T4Q1yg/AACAPwnNnD7G6rg8vFJ2vHY0trnjD2E/g2wWvvRVbz/ljkY6AACAP4VET78AwNy3VHgov5QHgL8AAIA/peuEPhVuhj5+Ios+uZ2TPtwMoT6fqbU+J9XVPsKRBT8caTc/AACAP+5qcj706lG73Zf4vNM8yjzcC4U/pHBLvaALSj8jTBQ/AACAP1kbUL8AAAC1eFgDv5Pzfz8AAAAArwuCPsOFgz4gIIg+ZWyQPiaRnT7Ju7E+MTXRPjSuAj+XcTM/AACAP63oKz40NLM7Oq9avRwPfry53U6/ncCWvqCCH79j1XK+AACAPy4/jj8AAAAAYPVQP/v/f78AAAAAu7ZtPtNpcD7J03g+Zv+DPqgCkD4dcaI+STW/Ps3f7j5BASQ/AACAP14CfD7Skae9xbEwOn1wEj2n6Tm/YpYhPyAf8b31/38/AAAAAMgMkT83gyc/SsD0PlWYKDwAAAAAodyCPhRZhD7X+og+cVSRPlCOnj5a2bI+VIXSPiuAAz/okTQ/AACAP6cwwT47bzc9czzOvdvKJT2El1C/AChsOihuL75Jxr69AACAPwVoNj+I5be+oFZvP6sKszcAAIA/c3mDPq73hD79nok+mgKSPlJMnz6tr7M+nIHTPsEdBD9LajU/AACAPw4xlD6J3788/CT0uwMRLz3CGpA/wEUeO3qN9D4JdSW9AACAPwv+Vb8A0KO4aK/AvrSQfz8AAIA/NzWCPsSvgz6ZS4g+hZqQPnjDnT6L9LE+AXjRPvDXAj/mqjM/AACAP2gUDD5vMdS6mghCPAaQHz3PnUi//5a3vRgaiL58cUa9AACAPwGdej9s9Ee/gy2KP+h02j8AAIA/k/psPoirbz7VDng+65aDPquQjz6J8KE+8J2+PjGY7j4YACI/AACAPyGCVj6kLBu9Pt1SPYp6Dj2ch40/gup/vjyKPD8AAIA/AAAAAMFFTr86Gza/yEuJvgMAgD8AAIA/56WFPnQqhz515Ys+k2yUPonuoT4uqLY+ygDXPuxMBj8eajg/AACAP8ad8T7donc912w+veY5grywDo0/PZrAvii8qb7//3+/AAAAAJ+OUb8BAIC/eKC7vlj/3r4AAIA//r2MPitXjj50UpM+c02cPvaGqj48WsA+YWriPuFtDT8Z1UU/AACAP2BvOD1Z5h+9NXaiPGn8gbx6Qku/7mIZPtIsjT4W5pU9AACAP2PRlT91BYA/+utVP7DQf78AAIA/ywJsPvCwbj54C3c+VQ2DPo/6jj43R6E+ota9Prwp7T591CI/AACAP6n8DT2yauU8uPjjPBGYorypIDa///9/v3CTtL4AAIA/AAAAAELtjj8AAAAADhlpP8H8T74AAIA/zWd3PhI3ej5tfIE+FmGJPrnhlT6OEKk++ADHPvuc+D4CsSo/AACAP8xrJT7NpnY8UdoZPZ1tTbwL90G/j6HmvZCi5760smu/AACAPzRqgT9CVlW/BlZvP6uqKrMAAAAAw9F0PoSZdz7uIYA+ePGHPqdQlD4mTKc+c+zEPrYD9j7/Eiw/AACAP/kJhD0pxie8TWdIPOBeJT3HvFW/gJ1WuqBJhTxiAoA/AAAAADXfjT8AgAA4AFZvP6BFkTsAAAAAyWxqPlIWbT56YnU+4iuCPpgEjj7FMaA+D5C8Pr6R6z6N5CI/Xrx8P249Kj7vlQu8iAtgPYAPeLz/bo4/DGSOvoJObz8AAAAAAAAAAFvMT7/+/3+/ADL2vEA5wz8AAAAAgLWFPjo6hz7J9Ys+5n2UPm8Boj6AvbY+4hnXPplcBj+jfzg/AACAP4wA+z5GfYI8WijXu/OCiDxuz0S/utYTPkiJIr8AAAAAAAAAAMFrTT86Sjy/QCD/PDcPJz8AAIA/M2qWPn8fmD5tcp0+bQunPjQ/tj54ks0+6/nxPiwmFz8zgUk/AACAP7NGIj5dp5W8n7JIvN2zK73who8/JFULPwIibD8AAAAAAAAAAK53UL8AAAAAAJuUvTlOyz4AAAAAL6GBPg0agz6lsIc+H/aPPhwQnT47KrE+3YnQPi9DAj+j3jI/AACAPwrE1T1xSQ89Xm2DvUSPkL2oRJE/rq4qvqgUXD8AAIA/AAAAAFAGF7+bRnu+KosJv/v/f78AAAAA0kaNPo3hjj6u4ZM+aOWcPr4sqz49FcE+gEbjPmD3DT/a8EI/AACAPwbi/j4klAi9siMAPTpsYr2NvFW/AAAAADx4y74kcw6/AAAAAGcjfD+yyYK+MJogvwAAAAAAAAAAkVyIPgLpiT6ZvI4+CnCXPjU4pT6UXbo+UF7bPvoGCT+mKDw/AACAPzOXNb+q3gC+WQ2aPtofTLy9OSc/PgDYPtjqE7/7/38/AAAAAA+oQL4Px6M/RlMTP/3/f78AAAAAAI+PPl0wkT4rRZY+LG6fPo3wrT6jM8Q+SfLmPmhCED/vFkY/AACAPzUCmj3qG0O6wL6HvP8Q2Ly7DlW/AACQMVBHGb8BAIC/AAAAAP1vjz8pSAm90ixmP1stHj8AAIA/QetwPquncz6rLnw+BceFPr7zkT7SoaQ+ScnBPlQY8j5bNyY/AACAPyrZtz3OTSq9G2QkPDRFrjyjcjm/ZiuwPpBRZD1DzmS+AACAP6BEkT8AgBu4RCBbPwAeVD8AAAAAqz9zPtsCdj73nn4+MhKHPg5dkz5hOaY+BanDPqdv9D7W0ic/AACAP5c8rj4CVRU6+943vTZlrjxfAoo/hhAiv5J29D45AYC/AAAAADO/Vb8A3FG2WJ+avmiCDz8AAIA/B9GFPhFWhz6ZEow+eJyUPskioj4f47Y+KkbXPkJ4Bj+fpTg/AACAP34LDz7C25c8TblhPMPDnzyvU1a/4Eh9u5AsVj3wtX6/AAAAAOVojT8AoJ04jNBKPykUWL4AAAAAPZdoPnA7az77dnM+JyeBPiPojD7o8J4+Xxa7Pui56T5reCA/AACAP3xhaD80QFA8QqK4vXvvMD0pWmA/OFGAP7ogAr/z+n+/AAAAAEcnVb++7F898p4iv8DmSDwAAAAAJ+iNPreEjz6OipQ+k5idPjjwqz678cE+CkrkPn+ZDj94z0M/AACAP7K5sz4u/c68HMW3PPsdR7kssoo/zMk8PloftD6E2Om8AACAP9rmVb8AADe2+PZjvnXlfz8AAIA/DHKFPgL2hj4ur4s+/DKUPrSvoT5PYbY+Xq3WPtEYBj+QIjg/AACAP8FGeD4R/sO8VN1BvNYv2ru3how/R2NcP/HJJD8AAIC/AACAP92PVL/MF6E9APYJveiGQT0AAIA/2bSBPvEtgz47xYc+9guQPu8nnT4bRbE+f6nQPvFWAj/F+TI/AACAPyJQvT47ykg9Jj8Hu/f7NLwvtlG/AXlev3z6ob5zE30/AACAP163Wz+5Im6/TaInPwAAgD8AAIA/hPGBPkxrgz68BIg+Vk+QPnFxnT4FmLE+GAvRPuiTAj98TTM/AACAP2Cepj57f/A7S0cAvRUgBDyZiVO/oMyFulZzG78F2y89AACAP2TJgD9VHga+WrfrPuDK5z0AAIA/kS98PrwMfz7q/IM+ngiMPhnHmD7RVKw+UtnKPrlq/T57cS0/AACAPwEFcz4SU8U8Eb1uvNI94bwVWlW/Vp0Av5J/C7/Y9WI/AACAPxM6kT8AAAAAIqZeP/v/f78AAAAAC+pxPlqpdD5fOX0+f1SGPhiOkj7uT6U+OpbCPl0Y8z4j5yY/AACAPwC0VD4TcxC9y0qcPB8pqTyUi4s/oQkKvmwKUT8BAIA/AACAP99fT7/nqKE+CCm+vkSthr4AAIA/syGAPjaWgT48H4Y+PUyOPng/mz4fHq8+8SDOPtTBAD98zTA/AACAPyihqT5rrqE7zog2vG3eTDxFElo/ripWvQpWbz8AgE62AACAP6VJUr8AAPCzmEQav7pCqD4AAIA/VCeFPnGqhj73YIs+AuCTPixVoT4x+7U+KzXWPrvNBT92uzc/AACAPxyxlT3660O6P1LWvF+8jDxRJDy/cXRSP4jmCD4AAIC/AACAPyQBjj8AAAAAWg9lPwS7B70AAAAAU+1uPvKjcT7mGHo+3auEPtG+kD5bRaM+Hi/APn4M7z7JvSE/AACAPzB+2z15qAK9jzQOPBYEiDv9l0S/JFCAvkDvwr4BAIA/AACAPx76jD8AAAAAFEpmP+EFMD8AAAAApZRvPitNcj4LyHo+xgiFPi8kkT6yt6M+tLXAPgzA8D76SiU/AACAPxd5bj6Za5y8rRp5vU5/S7xPl24/Qs52v2xubD/FANM/AACAP/rgLb/8PDk/pNEAv/v/fz8AAAAAgveJPp2Iiz7BapA+ajiZPh4qpz43j7w+aPPdPu2jCj8dG0A/AACAP7eKVz4vs2G9D4SiPc1wx7yBLBq/55IuPmggbL77/3+/AAAAAGWgjD8OKE6+HFZvP6uqKrMAAAAApNuJPm5siz6VTZA+eBmZPloIpz4habw+k8bdPuyHCj88OT4/AACAP2jAjz0jGu65Kod0Ow0osjs2wVW/gKlOOnQijL4P9H8/AAAAAJ4/kT9AuQm4rPRuPxX4tbsAAIA//81dPtdSYD6lLGg+yFN2PlZfhj4Ckpc+VGmyPi/j3j5eBxk/AACAP8rO7z37dmY9NpknvXKkxr2aEV2/+/9/vwAwfDuJbKo/AAAAADc7jz9vki++vu1tPwAAgD8AAIA/Q2lpPtkPbD7SUnQ+xpuBPl9njT5tgJ8+Tr+7PvSM6j5SCSE/AACAP8M9/D7CayC9sLVqvfec97xfnlo/TxiNPngtsz6tXrk9AACAP9ZWE78Fvzo/UIkiv6uqKjUAAAAAWXWSPiQflD45Tpk+mKaiPgF0sT40Ksg+hJzrPmEsEz9EF0o/AACAP9URaz5JfZ0722cbPJvHujubIYE/pQQJv0ThbD/Y/38/AAAAAJC8Vb8AAFw0kokiv1UrSDkAAIA/a1N+PmebgD6lG4U+1DiNPv4Smj4xy60+/pHMPj+R/z5Ldy8/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLQEsYhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -64.536, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 8, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.96, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-58-generic-x86_64-with-glibc2.17 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
|
|
|
|
| 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 0x7fcc14f4ad30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc14f4adc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc14f4ae50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc14f4aee0>", "_build": "<function ActorCriticPolicy._build at 0x7fcc14f4af70>", "forward": "<function ActorCriticPolicy.forward at 0x7fcc14f4e040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcc14f4e0d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc14f4e160>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcc14f4e1f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc14f4e280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc14f4e310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc14f4e3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcc14f458a0>"}, "verbose": false, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [24], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_np_random": null}, "n_envs": 64, "num_timesteps": 10027008, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677207370498747542, "learning_rate": 0.0001, "tensorboard_log": null, "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:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="}, "_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": 1224, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.96, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWV5QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMWS9ob21lL3JsL21pbmljb25kYTMvZW52cy9ybC9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgkMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxZL2hvbWUvcmwvbWluaWNvbmRhMy9lbnZzL3JsL2xpYi9weXRob24zLjgvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-58-generic-x86_64-with-glibc2.17 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
|
replay.mp4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa95bc731326bfb11821d56aaa79bc12369b4853dbc7d4401979826ac54daa0b
|
| 3 |
+
size 4159351
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 301.5954648118415, "std_reward": 34.359621472787126, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-24T03:35:52.206809"}
|