culteejen commited on
Commit
c6c6556
1 Parent(s): 1d2737a

Upload model to Hugging Face

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
BC-harcodemap-punish-stagnant.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb24964149f4372e23c2475223e71e207cd138af20fdab40e704de1478d904f6
3
- size 44151
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6a5e683381f970a0f6ff601e9e1b7c5cea2b26403e215e3b542f3ea475d0e5
3
+ size 44110
BC-harcodemap-punish-stagnant/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 0x7fa2928f5240>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa2928f52d0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa2928f5360>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa2928f53f0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7fa2928f5480>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7fa2928f5510>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa2928f55a0>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa2928f5630>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7fa2928f56c0>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa2928f5750>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa2928f57e0>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa2928f5870>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7fa2928e9bc0>"
21
  },
22
  "verbose": true,
23
  "policy_kwargs": {},
@@ -48,7 +48,7 @@
48
  "_num_timesteps_at_start": 0,
49
  "seed": null,
50
  "action_noise": null,
51
- "start_time": 1681928884688037255,
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:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAABJD5ELMQjFA6Qk0QlZqe0IAAMhCAADIQvINnEIz1FhCAADIQi+HIkLhd+lCi0abPwAAyEL0Ix9CBFgsQuCRcEIAAMhCAADIQqxtkkIBrmNCSjrtQqYmMj5BrWtCAADIQgeYJ0Ktlh1C2o5oQlyng0IAAMhCAADIQj1160IyR6g/ySxWQuI2I0LCUj5CMfSBQgAAyEIAAMhCMweUQmyDaUKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"
61
  },
62
  "_last_episode_starts": {
63
  ":type:": "<class 'numpy.ndarray'>",
@@ -70,7 +70,7 @@
70
  "_current_progress_remaining": -0.02400000000000002,
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'>",
@@ -80,7 +80,7 @@
80
  "n_steps": 2048,
81
  "gamma": 0.99,
82
  "gae_lambda": 0.95,
83
- "ent_coef": 0.0001,
84
  "vf_coef": 0.5,
85
  "max_grad_norm": 0.5,
86
  "batch_size": 64,
 
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 0x7f710c4f91b0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f710c4f9240>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f710c4f92d0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f710c4f9360>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f710c4f93f0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f710c4f9480>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f710c4f9510>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f710c4f95a0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f710c4f9630>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f710c4f96c0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f710c4f9750>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f710c4f97e0>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f710c4e6dc0>"
21
  },
22
  "verbose": true,
23
  "policy_kwargs": {},
 
48
  "_num_timesteps_at_start": 0,
49
  "seed": null,
50
  "action_noise": null,
51
+ "start_time": 1681929994631146290,
52
  "learning_rate": 0.0003,
53
  "tensorboard_log": null,
54
  "lr_schedule": {
 
57
  },
58
  "_last_obs": {
59
  ":type:": "<class 'numpy.ndarray'>",
60
+ ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAH+v0EJdz9O/AADIQgAAyEJCN1tClYpFQlg+fELZkF9Cdi2NQq0PjkKx5OlCtp0vPrutU0IAAMhCEEq9QazfoUHbd8lBbnyYQgAAyEIAAMhCfwADQ2/kvj9fLdlBehyuQVm0ykHlwFVCAADIQgAAyEJG4ohCAADIQlxz6kJhSxLAAADIQgAAyEIAAMhC2iiAQgAAyEKMXE9C6K1NQmTgZkKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"
61
  },
62
  "_last_episode_starts": {
63
  ":type:": "<class 'numpy.ndarray'>",
 
70
  "_current_progress_remaining": -0.02400000000000002,
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'>",
 
80
  "n_steps": 2048,
81
  "gamma": 0.99,
82
  "gae_lambda": 0.95,
83
+ "ent_coef": 0.001,
84
  "vf_coef": 0.5,
85
  "max_grad_norm": 0.5,
86
  "batch_size": 64,
BC-harcodemap-punish-stagnant/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b8b7a988362120763cc8055ccbca764649c058999722e1ed35e8e75b81d0d94
3
  size 18973
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd415f9a3139233306910cc235ccd5f54b2efafe7e9b78942c3764d15f4f178d
3
  size 18973
BC-harcodemap-punish-stagnant/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f461f021a953dd3052f94ac4943b5c816661382f1665ce149dae830b56f722dc
3
  size 9295
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58f3711ecc057277c083f77ece978e9f5667273d1c4d902817cf433918c15ff
3
  size 9295
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: RoombaAToB-harcodemap-punish-stagnant
17
  metrics:
18
  - type: mean_reward
19
- value: -106.05 +/- 0.00
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: RoombaAToB-harcodemap-punish-stagnant
17
  metrics:
18
  - type: mean_reward
19
+ value: -225.88 +/- 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 0x7fa2928f5240>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa2928f52d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa2928f5360>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa2928f53f0>", "_build": "<function ActorCriticPolicy._build at 0x7fa2928f5480>", "forward": "<function ActorCriticPolicy.forward at 0x7fa2928f5510>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa2928f55a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa2928f5630>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa2928f56c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa2928f5750>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa2928f57e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa2928f5870>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa2928e9bc0>"}, "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": 204800, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681928884688037255, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAABJD5ELMQjFA6Qk0QlZqe0IAAMhCAADIQvINnEIz1FhCAADIQi+HIkLhd+lCi0abPwAAyEL0Ix9CBFgsQuCRcEIAAMhCAADIQqxtkkIBrmNCSjrtQqYmMj5BrWtCAADIQgeYJ0Ktlh1C2o5oQlyng0IAAMhCAADIQj1160IyR6g/ySxWQuI2I0LCUj5CMfSBQgAAyEIAAMhCMweUQmyDaUKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 250, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0001, "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 0x7f710c4f91b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f710c4f9240>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f710c4f92d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f710c4f9360>", "_build": "<function ActorCriticPolicy._build at 0x7f710c4f93f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f710c4f9480>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f710c4f9510>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f710c4f95a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f710c4f9630>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f710c4f96c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f710c4f9750>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f710c4f97e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f710c4e6dc0>"}, "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": 204800, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681929994631146290, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV4QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAH+v0EJdz9O/AADIQgAAyEJCN1tClYpFQlg+fELZkF9Cdi2NQq0PjkKx5OlCtp0vPrutU0IAAMhCEEq9QazfoUHbd8lBbnyYQgAAyEIAAMhCfwADQ2/kvj9fLdlBehyuQVm0ykHlwFVCAADIQgAAyEJG4ohCAADIQlxz6kJhSxLAAADIQgAAyEIAAMhC2iiAQgAAyEKMXE9C6K1NQmTgZkKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 250, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.001, "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
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -106.05492408752445, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-19T11:42:17.674767"}
 
1
+ {"mean_reward": -225.88466445922876, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-19T12:01:49.557022"}