Upload model to Hugging Face
Browse files- PPO-default.zip +2 -2
- PPO-default/data +23 -23
- PPO-default/policy.optimizer.pth +2 -2
- PPO-default/policy.pth +2 -2
- PPO-default/system_info.txt +4 -4
- README.md +1 -1
- config.json +1 -1
- results.json +1 -1
PPO-default.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 sha256:90d7f233e8334111623469283bb374ee43aea00f0c6e61cbf60aa2f65f265367
|
| 3 |
+
size 142406
|
PPO-default/data
CHANGED
|
@@ -4,34 +4,34 @@
|
|
| 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._abc_data object at
|
| 21 |
},
|
| 22 |
"verbose": true,
|
| 23 |
"policy_kwargs": {},
|
| 24 |
"observation_space": {
|
| 25 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 26 |
-
":serialized:": "
|
| 27 |
"dtype": "float32",
|
| 28 |
"_shape": [
|
| 29 |
-
|
| 30 |
],
|
| 31 |
-
"low": "[-600. -400. 0.]",
|
| 32 |
-
"high": "[600. 400. 3.1415927]",
|
| 33 |
-
"bounded_below": "[ True True True]",
|
| 34 |
-
"bounded_above": "[ True True True]",
|
| 35 |
"_np_random": null
|
| 36 |
},
|
| 37 |
"action_space": {
|
|
@@ -48,16 +48,16 @@
|
|
| 48 |
"_num_timesteps_at_start": 0,
|
| 49 |
"seed": null,
|
| 50 |
"action_noise": null,
|
| 51 |
-
"start_time":
|
| 52 |
"learning_rate": 0.0003,
|
| 53 |
"tensorboard_log": null,
|
| 54 |
"lr_schedule": {
|
| 55 |
":type:": "<class 'function'>",
|
| 56 |
-
":serialized:": "
|
| 57 |
},
|
| 58 |
"_last_obs": {
|
| 59 |
":type:": "<class 'numpy.ndarray'>",
|
| 60 |
-
":serialized:": "
|
| 61 |
},
|
| 62 |
"_last_episode_starts": {
|
| 63 |
":type:": "<class 'numpy.ndarray'>",
|
|
@@ -70,7 +70,7 @@
|
|
| 70 |
"_current_progress_remaining": -0.010346666666666726,
|
| 71 |
"ep_info_buffer": {
|
| 72 |
":type:": "<class 'collections.deque'>",
|
| 73 |
-
":serialized:": "
|
| 74 |
},
|
| 75 |
"ep_success_buffer": {
|
| 76 |
":type:": "<class 'collections.deque'>",
|
|
|
|
| 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 0x7f77d73d8c10>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f77d73d8ca0>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f77d73d8d30>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f77d73d8dc0>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f77d73d8e50>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f77d73d8ee0>",
|
| 13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f77d73d8f70>",
|
| 14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f77d73d9000>",
|
| 15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f77d73d9090>",
|
| 16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f77d73d9120>",
|
| 17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f77d73d91b0>",
|
| 18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f77d73d9240>",
|
| 19 |
"__abstractmethods__": "frozenset()",
|
| 20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f77d73cf800>"
|
| 21 |
},
|
| 22 |
"verbose": true,
|
| 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 |
+
6
|
| 30 |
],
|
| 31 |
+
"low": "[-600. -400. 0. 0. 0. 0.]",
|
| 32 |
+
"high": "[600. 400. 3.1415927 1. 1. 1. ]",
|
| 33 |
+
"bounded_below": "[ True True True True True True]",
|
| 34 |
+
"bounded_above": "[ True True True True True True]",
|
| 35 |
"_np_random": null
|
| 36 |
},
|
| 37 |
"action_space": {
|
|
|
|
| 48 |
"_num_timesteps_at_start": 0,
|
| 49 |
"seed": null,
|
| 50 |
"action_noise": null,
|
| 51 |
+
"start_time": 1679966528268454497,
|
| 52 |
"learning_rate": 0.0003,
|
| 53 |
"tensorboard_log": null,
|
| 54 |
"lr_schedule": {
|
| 55 |
":type:": "<class 'function'>",
|
| 56 |
+
":serialized:": "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"
|
| 57 |
},
|
| 58 |
"_last_obs": {
|
| 59 |
":type:": "<class 'numpy.ndarray'>",
|
| 60 |
+
":serialized:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAKqG6UI3GhvD9NQUwOc3Ez8AAIA/AACAP9CoscKGxrXCmaUDwQAAgD8AAIA/AACAP+jgokLiXNXCW62RwAAAgD8AAIA/AACAP3ouecLoGVvC4eZawAAAgD8AAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsGhpSMAUOUdJRSlC4="
|
| 61 |
},
|
| 62 |
"_last_episode_starts": {
|
| 63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
|
| 70 |
"_current_progress_remaining": -0.010346666666666726,
|
| 71 |
"ep_info_buffer": {
|
| 72 |
":type:": "<class 'collections.deque'>",
|
| 73 |
+
":serialized:": "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"
|
| 74 |
},
|
| 75 |
"ep_success_buffer": {
|
| 76 |
":type:": "<class 'collections.deque'>",
|
PPO-default/policy.optimizer.pth
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:d3d59eb5c29e1d8752371bf7dd15baccf9894b768c79fc137a3fb55c6df8e371
|
| 3 |
+
size 86009
|
PPO-default/policy.pth
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:e3d426cf280c8be36e3eb5c80c28b40f30899371dd002e0add29e85efc48726f
|
| 3 |
+
size 42369
|
PPO-default/system_info.txt
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
-
- OS: Linux-5.
|
| 2 |
- Python: 3.10.9
|
| 3 |
- Stable-Baselines3: 1.7.0
|
| 4 |
-
- PyTorch:
|
| 5 |
-
- GPU Enabled:
|
| 6 |
-
- Numpy: 1.
|
| 7 |
- Gym: 0.21.0
|
|
|
|
| 1 |
+
- OS: Linux-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2
|
| 2 |
- Python: 3.10.9
|
| 3 |
- Stable-Baselines3: 1.7.0
|
| 4 |
+
- PyTorch: 2.0.0
|
| 5 |
+
- GPU Enabled: True
|
| 6 |
+
- Numpy: 1.23.5
|
| 7 |
- Gym: 0.21.0
|
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
type: RoombaAToB
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value:
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 16 |
type: RoombaAToB
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: -77.43 +/- 39.16
|
| 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 0x7fdba63bf9a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdba63bfa30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdba63bfac0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdba63bfb50>", "_build": "<function ActorCriticPolicy._build at 0x7fdba63bfbe0>", "forward": "<function ActorCriticPolicy.forward at 0x7fdba63bfc70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fdba63bfd00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdba63bfd90>", "_predict": "<function ActorCriticPolicy._predict at 0x7fdba63bfe20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdba63bfeb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdba63bff40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdba63c8040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fdba63c4dc0>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-600. -400. 0.]", "high": "[600. 400. 3.1415927]", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 303104, "_total_timesteps": 300000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678477056917472370, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVpQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYwAAAAAAAAAC4LYcLVoatCmIQHQPJgIENVgQrDgZSBvx1S5MGgWjXDhlKgwBHqfMIvhopCgepYwJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsDhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.010346666666666726, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 370, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.0-9-amd64-x86_64-with-glibc2.31 # 1 SMP Debian 5.10.70-1 (2021-09-30)", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "False", "Numpy": "1.24.1", "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 0x7f77d73d8c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f77d73d8ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f77d73d8d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f77d73d8dc0>", "_build": "<function ActorCriticPolicy._build at 0x7f77d73d8e50>", "forward": "<function ActorCriticPolicy.forward at 0x7f77d73d8ee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f77d73d8f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f77d73d9000>", "_predict": "<function ActorCriticPolicy._predict at 0x7f77d73d9090>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f77d73d9120>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f77d73d91b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f77d73d9240>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f77d73cf800>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [6], "low": "[-600. -400. 0. 0. 0. 0.]", "high": "[600. 400. 3.1415927 1. 1. 1. ]", "bounded_below": "[ True True True True True True]", "bounded_above": "[ True True True True True True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 303104, "_total_timesteps": 300000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679966528268454497, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAKqG6UI3GhvD9NQUwOc3Ez8AAIA/AACAP9CoscKGxrXCmaUDwQAAgD8AAIA/AACAP+jgokLiXNXCW62RwAAAgD8AAIA/AACAP3ouecLoGVvC4eZawAAAgD8AAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsGhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.010346666666666726, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 370, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "2.0.0", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": -77.4299756, "std_reward": 39.15808347387722, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-27T18:28:24.184327"}
|