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 sha256:37e7d8577ae93aef8c83e7fe45b5d3a5de0474eaccd3d8bcbb01464005c8b3f0
|
3 |
+
size 44057
|
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 0x7ff3a7af12d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3a7af1360>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3a7af13f0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3a7af1480>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff3a7af1510>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff3a7af15a0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3a7af1630>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3a7af16c0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff3a7af1750>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3a7af17e0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3a7af1870>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3a7af1900>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff3a7aded00>"
|
21 |
},
|
22 |
"verbose": true,
|
23 |
"policy_kwargs": {},
|
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 4,
|
46 |
+
"num_timesteps": 65536,
|
47 |
+
"_total_timesteps": 60000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1681941051662804231,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAJbeD0MGOjJAKAQNQttn7EEAAMhCAADIQgAAyEI3KrZCwe9nQoa/SUI14pBCjV1hP5NzPkIAAMhCAADIQgAAyEIAAMhCAADIQspRDkK+ngJCnRjaQoSxkr4/ZFJCAADIQgAAyEIoyO1BBJrxQfINXEJEp7FCAADIQsITwEIGdOM+GJUIQgAAyEIRvjhCfrpDQuxcpkIAAMhCAADIQvpBOkKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.09226666666666672,
|
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": 80,
|
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:f10663a2bca9c635874f2ba550b9c09e450ae40a811927a5628e5c35d63571dc
|
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:a237dca00b1ad082d2fc11a39c6a4ca1c4b4d0bf1f674116af1669a4ab7776f6
|
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: -96.82 +/- 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 0x7f36f68e52d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f36f68e5360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f36f68e53f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f36f68e5480>", "_build": "<function ActorCriticPolicy._build at 0x7f36f68e5510>", "forward": "<function ActorCriticPolicy.forward at 0x7f36f68e55a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f36f68e5630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f36f68e56c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f36f68e5750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f36f68e57e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f36f68e5870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f36f68e5900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f36f68d23c0>"}, "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": 24576, "_total_timesteps": 20000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681940879795278580, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAANZ6rELTgiU/AADIQgAAyEIxQZhC3imjQgAAyEL0e69CbxKPQgAAyELf5OJCkscNPwAAyEIAAMhCU/4jQt9gNkKqFX5CAADIQgAAyEKfzn1C+wjkQiA6KT8AAMhCAABIQgAAIEIAAEhCAACMQgAAyEIAAMhC8zxpQiz0i0IZiwNAAADIQgAAyEIs6JlCAADIQgAAyEIAAMhCAADIQgAAyEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.2287999999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 30, "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 0x7ff3a7af12d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3a7af1360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3a7af13f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3a7af1480>", "_build": "<function ActorCriticPolicy._build at 0x7ff3a7af1510>", "forward": "<function ActorCriticPolicy.forward at 0x7ff3a7af15a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3a7af1630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3a7af16c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff3a7af1750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3a7af17e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3a7af1870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3a7af1900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff3a7aded00>"}, "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": 1681941051662804231, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAJbeD0MGOjJAKAQNQttn7EEAAMhCAADIQgAAyEI3KrZCwe9nQoa/SUI14pBCjV1hP5NzPkIAAMhCAADIQgAAyEIAAMhCAADIQspRDkK+ngJCnRjaQoSxkr4/ZFJCAADIQgAAyEIoyO1BBJrxQfINXEJEp7FCAADIQsITwEIGdOM+GJUIQgAAyEIRvjhCfrpDQuxcpkIAAMhCAADIQvpBOkKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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:": "gAWV4QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "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:a2eddd4fb095654348c8a70f9582f9b383953249f3c1c11c0f8b249907134931
|
3 |
+
size 1255693
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": -96.8167945098878, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-19T14:55:23.319172"}
|