Upload model to Hugging Face
Browse files- BC-harcodemap-punish-stagnant-no-training.zip +2 -2
- BC-harcodemap-punish-stagnant-no-training/data +20 -20
- BC-harcodemap-punish-stagnant-no-training/policy.optimizer.pth +1 -1
- BC-harcodemap-punish-stagnant-no-training/policy.pth +1 -1
- README.md +1 -1
- config.json +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
BC-harcodemap-punish-stagnant-no-training.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 sha256:27998aca8f37c40a8ed3d5128153e08b1c0a1bdb02f03ce0e81ba6b228e98665
|
3 |
+
size 44052
|
BC-harcodemap-punish-stagnant-no-training/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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": {},
|
@@ -43,12 +43,12 @@
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 4,
|
46 |
-
"num_timesteps":
|
47 |
-
"_total_timesteps":
|
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": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -67,16 +67,16 @@
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
-
"_current_progress_remaining": -0.
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
-
"_n_updates":
|
80 |
"n_steps": 2048,
|
81 |
"gamma": 0.99,
|
82 |
"gae_lambda": 0.95,
|
|
|
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 0x7f31e51f52d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f31e51f5360>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f31e51f53f0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f31e51f5480>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f31e51f5510>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f31e51f55a0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f31e51f5630>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f31e51f56c0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f31e51f5750>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f31e51f57e0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f31e51f5870>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f31e51f5900>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f31e51e2540>"
|
21 |
},
|
22 |
"verbose": true,
|
23 |
"policy_kwargs": {},
|
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 4,
|
46 |
+
"num_timesteps": 57344,
|
47 |
+
"_total_timesteps": 50000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1681942405434605801,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAADHVBEMGgwe/AADIQgXTlEIdJ3lC74MXQoRSFkIrzypC4h5NQgAAyEL70c1CoiU3v8ZJxEIBNENCAADIQo4LXkLCfVVCBIaQQgAAyEIAAMhCdEmuQiQLKEBWBbNCAADIQgAAyEIAAMhC7S1bQiMrMUIyqFBCu4OvQgH9vELWuRa/hN2MQrJ4K0IAAMhCe+6BQrRMhEJwmZ1CAADIQgAAyEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.1468799999999999,
|
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'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
+
"_n_updates": 70,
|
80 |
"n_steps": 2048,
|
81 |
"gamma": 0.99,
|
82 |
"gae_lambda": 0.95,
|
BC-harcodemap-punish-stagnant-no-training/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18973
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af793150ab7e28a9a103588a40f15aa4093e8ae22ae29440f5c4c3ed84fd89ff
|
3 |
size 18973
|
BC-harcodemap-punish-stagnant-no-training/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9295
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be73d87f16c3f4459e504e368b82811b9e47b411e2d64efe096b475af4658643
|
3 |
size 9295
|
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: RoombaAToB-harcodemap-punish-stagnant-no-training
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: RoombaAToB-harcodemap-punish-stagnant-no-training
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -9.04 +/- 0.00
|
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 0x7fc03a5f52d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc03a5f5360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc03a5f53f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc03a5f5480>", "_build": "<function ActorCriticPolicy._build at 0x7fc03a5f5510>", "forward": "<function ActorCriticPolicy.forward at 0x7fc03a5f55a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc03a5f5630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc03a5f56c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc03a5f5750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc03a5f57e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc03a5f5870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc03a5f5900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc03a5f1680>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [10], "low": "[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]", "high": "[5.2000000e+05 3.1415927e+00 1.0000000e+02 1.0000000e+02 1.0000000e+02\n 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02]", "bounded_below": "[ True True True True True True True True True True]", "bounded_above": "[ True True True True True True True True True True]", "_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": 4, "num_timesteps": 65536, "_total_timesteps": 60000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681941780212283514, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAD5xI0P8C4I/IWNsQmKrv0G6r4tBnHYzQR7RQUEAAMhCAADIQgAAyEJRYgJDKhURPwAAyEIAAEhCAAAgQvM8aUIAAEhCAADIQgAAyELoC6xCqOwKQ+MvBz+a7KRCAABIQgAAIELYOBBCAAAgQgAAyEIAAMhC/K28QqjsCkPjLwc/muykQgAASEIAACBC2DgQQgAAIEIAAMhCAADIQvytvEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"}, "_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": -0.09226666666666672, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 80, "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"}}
|
|
|
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 0x7f31e51f52d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f31e51f5360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f31e51f53f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f31e51f5480>", "_build": "<function ActorCriticPolicy._build at 0x7f31e51f5510>", "forward": "<function ActorCriticPolicy.forward at 0x7f31e51f55a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f31e51f5630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f31e51f56c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f31e51f5750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f31e51f57e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f31e51f5870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f31e51f5900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f31e51e2540>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [10], "low": "[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]", "high": "[5.2000000e+05 3.1415927e+00 1.0000000e+02 1.0000000e+02 1.0000000e+02\n 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02]", "bounded_below": "[ True True True True True True True True True True]", "bounded_above": "[ True True True True True True True True True True]", "_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": 4, "num_timesteps": 57344, "_total_timesteps": 50000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681942405434605801, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAADHVBEMGgwe/AADIQgXTlEIdJ3lC74MXQoRSFkIrzypC4h5NQgAAyEL70c1CoiU3v8ZJxEIBNENCAADIQo4LXkLCfVVCBIaQQgAAyEIAAMhCdEmuQiQLKEBWBbNCAADIQgAAyEIAAMhC7S1bQiMrMUIyqFBCu4OvQgH9vELWuRa/hN2MQrJ4K0IAAMhCe+6BQrRMhEJwmZ1CAADIQgAAyEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"}, "_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": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVOhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIuaZAZidHecCUhpRSlIwBbJRLvIwBdJRHQGChg8Swnpl1fZQoaAZoCWgPQwimtP6WAAl6wJSGlFKUaBVLDmgWR0BgpoLmZE2HdX2UKGgGaAloD0MIccyyJ8HDdsCUhpRSlGgVS4FoFkdAYKcKekHlfnV9lChoBmgJaA9DCFZKz/Sy0ILAlIaUUpRoFUtIaBZHQGCx3sgMc6x1fZQoaAZoCWgPQwg91SE3Y3iFwJSGlFKUaBVLjmgWR0Bh2pzLfUF0dX2UKGgGaAloD0MIibMiauKge8CUhpRSlGgVS2BoFkdAYeF7Lt/nXHV9lChoBmgJaA9DCNWuCWmNF4LAlIaUUpRoFUuKaBZHQGHk5pJwsGx1fZQoaAZoCWgPQwhfKcsQpxWFwJSGlFKUaBVLU2gWR0Bh+G4qgAZLdX2UKGgGaAloD0MIfGXeqosygcCUhpRSlGgVS0hoFkdAYfiona37UHV9lChoBmgJaA9DCJS9pZxPpoXAlIaUUpRoFUulaBZHQGIIzQu27Wd1fZQoaAZoCWgPQwhXlX1X5JCCwJSGlFKUaBVLQ2gWR0BiCZX6qKgqdX2UKGgGaAloD0MI5q26DpXVgsCUhpRSlGgVS05oFkdAYg2i2UjcEnV9lChoBmgJaA9DCOFdLuI7fFfAlIaUUpRoFU0tAWgWR0BiEbO5avA5dX2UKGgGaAloD0MIPYBFfj2we8CUhpRSlGgVS1xoFkdAYicnc+JP7HV9lChoBmgJaA9DCGPVIMztInnAlIaUUpRoFUtmaBZHQGI08e0Xxe91fZQoaAZoCWgPQwjtnGaB1hiCwJSGlFKUaBVLOmgWR0BiPGhoM8YAdX2UKGgGaAloD0MIYk1lUbhpg8CUhpRSlGgVS9poFkdAYlYCNCJGfHV9lChoBmgJaA9DCB1xyAaSE3vAlIaUUpRoFUtdaBZHQGJZLNnoPkJ1fZQoaAZoCWgPQwi06J0KuJd5wJSGlFKUaBVLb2gWR0BiZ8CT2WY4dX2UKGgGaAloD0MIqYjTSTYhZMCUhpRSlGgVTS0BaBZHQGJ6h4Uvf0p1fZQoaAZoCWgPQwj4bvPGyRN7wJSGlFKUaBVLYmgWR0BifW3DvVmSdX2UKGgGaAloD0MI2bRSCOSNecCUhpRSlGgVS19oFkdAYon5k9U0enV9lChoBmgJaA9DCGUaTS4GU4TAlIaUUpRoFUubaBZHQGKPiDmKZUl1fZQoaAZoCWgPQwjkEHFzKv96wJSGlFKUaBVLa2gWR0BitWwLVnVYdX2UKGgGaAloD0MIfCb752lWgsCUhpRSlGgVSztoFkdAYsziEQGwA3V9lChoBmgJaA9DCKg3o+YroXnAlIaUUpRoFUu3aBZHQGLay6MBIWh1fZQoaAZoCWgPQwgnSkIibdNWwJSGlFKUaBVNLQFoFkdAYvQA7PppvnV9lChoBmgJaA9DCCZzLO+qvlzAlIaUUpRoFU0tAWgWR0Bi9zwF1SwXdX2UKGgGaAloD0MIn69ZLnsggsCUhpRSlGgVS0VoFkdAYvhwCr92o3V9lChoBmgJaA9DCM10r5P6aF7AlIaUUpRoFU0tAWgWR0BjRUUoKD02dX2UKGgGaAloD0MII0vmWB6SgcCUhpRSlGgVS+toFkdAY0/fKISDiHV9lChoBmgJaA9DCDKuuDgqJ1rAlIaUUpRoFU0tAWgWR0BjbX1+RYA9dX2UKGgGaAloD0MIOwDirl6pWMCUhpRSlGgVTS0BaBZHQGNt+TvAoG91fZQoaAZoCWgPQwiduvJZ/nGDwJSGlFKUaBVLR2gWR0BjiKYoiLVGdX2UKGgGaAloD0MIpYXLKsyMgsCUhpRSlGgVSy9oFkdAY5qMI/qxDHV9lChoBmgJaA9DCFpJK74Bw4LAlIaUUpRoFUtGaBZHQGOzNXgccVB1fZQoaAZoCWgPQwgFptO6DXoRwJSGlFKUaBVNLQFoFkdAY7fIPsiSq3V9lChoBmgJaA9DCECiCRSxOFbAlIaUUpRoFU0tAWgWR0Bjve0w8GLUdX2UKGgGaAloD0MImIV2TrONZsCUhpRSlGgVTS0BaBZHQGPP0PYnOSp1fZQoaAZoCWgPQwhy32qdOH6EwJSGlFKUaBVLmWgWR0Bj24Cr92ovdX2UKGgGaAloD0MIN4sXC+PYg8CUhpRSlGgVS4toFkdAY9uOQQtjC3V9lChoBmgJaA9DCH1BCwkYkHrAlIaUUpRoFUtVaBZHQGPk7aIvalF1fZQoaAZoCWgPQwhFup9TEIxlwJSGlFKUaBVNLQFoFkdAZAW5nUUfxXV9lChoBmgJaA9DCKPlQA/1eXjAlIaUUpRoFUvIaBZHQGQIT7uUliV1fZQoaAZoCWgPQwjyeFp+IJKDwJSGlFKUaBVNIAFoFkdAZCO2E0zj3nV9lChoBmgJaA9DCPVnP1LEL3vAlIaUUpRoFUtYaBZHQGQj5LRKHwh1fZQoaAZoCWgPQwinlq31ReWCwJSGlFKUaBVLimgWR0BkL+/UONHZdX2UKGgGaAloD0MIkXu6umNVTcCUhpRSlGgVTS0BaBZHQGQ3dWyTpxF1fZQoaAZoCWgPQwhzgctj7WCDwJSGlFKUaBVLjGgWR0BkVkxyn1nNdX2UKGgGaAloD0MIDk3Z6Ye3esCUhpRSlGgVS2RoFkdAZF5hmXgLqnV9lChoBmgJaA9DCJaUu88RRYPAlIaUUpRoFUuNaBZHQGRlvJ7sv7F1fZQoaAZoCWgPQwh+x/DY7xCCwJSGlFKUaBVLNWgWR0BkakDhcZ+AdX2UKGgGaAloD0MIfF9cqlJydcCUhpRSlGgVSypoFkdAZGy3juKGcnV9lChoBmgJaA9DCAkzbf8K74LAlIaUUpRoFUvSaBZHQGRvyPMjeKt1fZQoaAZoCWgPQwgw16IFSF2EwJSGlFKUaBVLmmgWR0BlnpegL7XQdX2UKGgGaAloD0MI78ftl2/IgsCUhpRSlGgVS5ZoFkdAZaJLi++M63V9lChoBmgJaA9DCF1txf6yhYTAlIaUUpRoFUveaBZHQGWqAGbCrLh1fZQoaAZoCWgPQwh7TKQ0mwl6wJSGlFKUaBVLUmgWR0Blr8DU3GXHdX2UKGgGaAloD0MIsHPTZvx1gsCUhpRSlGgVSyxoFkdAZbJAfMfRu3V9lChoBmgJaA9DCL3GLlG9c0fAlIaUUpRoFU0tAWgWR0Blv1SqEOAidX2UKGgGaAloD0MIqS9LO/WlgcCUhpRSlGgVSz1oFkdAZcAPe54GEHV9lChoBmgJaA9DCGvWGd/XXn3AlIaUUpRoFU0IAWgWR0Bl4AcrAgxKdX2UKGgGaAloD0MIl1KXjCNkg8CUhpRSlGgVS4doFkdAZeWrmQr+YXV9lChoBmgJaA9DCC3OGObEYoLAlIaUUpRoFUvVaBZHQGXl88La24N1fZQoaAZoCWgPQwjko8UZA6d7wJSGlFKUaBVLaGgWR0BmAa42CNCJdX2UKGgGaAloD0MIQC/cuTDxecCUhpRSlGgVSw5oFkdAZgTRkVeruXV9lChoBmgJaA9DCE6XxcRmimLAlIaUUpRoFU0tAWgWR0BmFr8Nx2jgdX2UKGgGaAloD0MIDcaIRCGSg8CUhpRSlGgVS9JoFkdAZiWKVII4VHV9lChoBmgJaA9DCLMkQE0tdlzAlIaUUpRoFU0tAWgWR0BmQE3wTdtVdX2UKGgGaAloD0MImIbhI0KFg8CUhpRSlGgVS95oFkdAZkfpeNT99HV9lChoBmgJaA9DCP36ITa4KoLAlIaUUpRoFUuhaBZHQGZIARChN/R1fZQoaAZoCWgPQwi37XvUnwqDwJSGlFKUaBVLdmgWR0BmSixu89OidX2UKGgGaAloD0MIMQqCx9c8gsCUhpRSlGgVSy5oFkdAZlBopQUHp3V9lChoBmgJaA9DCPSKpx4J5YLAlIaUUpRoFUs6aBZHQGZbdoWYWtV1fZQoaAZoCWgPQwgIqkav5mGCwJSGlFKUaBVLRmgWR0BmaZElVtGedX2UKGgGaAloD0MIv56vWS7cUsCUhpRSlGgVTS0BaBZHQGazu45Lh751fZQoaAZoCWgPQwhGzVfJx2FYwJSGlFKUaBVNLQFoFkdAZrVEkSmIkHV9lChoBmgJaA9DCGxB742hAoLAlIaUUpRoFU0mAWgWR0BmxqtPpIMCdX2UKGgGaAloD0MIBkfJq3NQUMCUhpRSlGgVTS0BaBZHQGbW2St/4It1fZQoaAZoCWgPQwi4WicuBwKCwJSGlFKUaBVLNGgWR0Bm2lHhCMP0dX2UKGgGaAloD0MI16GakqwNe8CUhpRSlGgVS1loFkdAZvdFdcB2fXV9lChoBmgJaA9DCAaf5uRFkHrAlIaUUpRoFUtlaBZHQGb4VvMr3Cd1fZQoaAZoCWgPQwjji/Z4IWFYwJSGlFKUaBVNLQFoFkdAZxpFglWwNnV9lChoBmgJaA9DCOm5ha5EPk/AlIaUUpRoFU0tAWgWR0BnG4ZXMhX9dX2UKGgGaAloD0MICd/7GzSDeMCUhpRSlGgVS3VoFkdAZx3Qrtmcv3V9lChoBmgJaA9DCLFvJxEBHIXAlIaUUpRoFU0fAWgWR0BnVLc/MW43dX2UKGgGaAloD0MIll0wuCaVgsCUhpRSlGgVTRoBaBZHQGdyTQ/oq1B1fZQoaAZoCWgPQwgLKT+p9sdTwJSGlFKUaBVNLQFoFkdAZ3emu1WsBHV9lChoBmgJaA9DCBvV6UDWbU7AlIaUUpRoFU0tAWgWR0Bnebx9XtBwdX2UKGgGaAloD0MIliU6y4xag8CUhpRSlGgVS9hoFkdAZ4jQAMlTnHV9lChoBmgJaA9DCMI1d/Q/KYPAlIaUUpRoFUuLaBZHQGeS8s+V1Ol1fZQoaAZoCWgPQwi/nq9Z7vaCwJSGlFKUaBVLPWgWR0BnlMMspXp4dX2UKGgGaAloD0MI1As+zUkpZ8CUhpRSlGgVTS0BaBZHQGe3VfeDWbx1fZQoaAZoCWgPQwhUrBqEGdqCwJSGlFKUaBVLk2gWR0BnusJa7mMgdX2UKGgGaAloD0MIKSUEq+pVL8CUhpRSlGgVTS0BaBZHQGfBLS3LFGZ1fZQoaAZoCWgPQwicMjffCO+AwJSGlFKUaBVLP2gWR0BnzBNGmUGFdX2UKGgGaAloD0MIKsWOxqEpfMCUhpRSlGgVS8JoFkdAZ81FDv3JxXV9lChoBmgJaA9DCJZ5q67jTYLAlIaUUpRoFUs9aBZHQGfPQe/5+H91fZQoaAZoCWgPQwgsnQ/PkpiCwJSGlFKUaBVLP2gWR0Bn5giHIp6QdX2UKGgGaAloD0MIatrFNLOVgMCUhpRSlGgVS0RoFkdAZ+ZaC+UQkHVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 70, "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"}}
|
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 sha256:717b0ef28e3d5b6d7bc6a2305677ab01b162927ba7c27741edcff5a4bcbdee8e
|
3 |
+
size 1275574
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -9.036662678060344, "std_reward": 1.7763568394002505e-15, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-19T15:17:00.897715"}
|