culteejen commited on
Commit
66c582d
1 Parent(s): 46ff734

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-from-behavior-cloning.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:829e55e505d6dab71065bed98e1f7fd463d3d8e3647621c8caac311e9aae9812
3
- size 44072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87152f991060b34ac5d5769ccd8eadbfb203a8679a664c042f682e1ac50304f0
3
+ size 44084
BC-from-behavior-cloning/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 0x7fa28a2f12d0>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa28a2f1360>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa28a2f13f0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa28a2f1480>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7fa28a2f1510>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7fa28a2f15a0>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa28a2f1630>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa28a2f16c0>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7fa28a2f1750>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa28a2f17e0>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa28a2f1870>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa28a2f1900>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7fa28a2de8c0>"
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": 1681848321440440409,
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:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAADHwh0Ooh6+/AADIQgAAyEIGD+9BAADIQnuGHEJ0LOBBZL/nQQAAyEK1u3BD6m8pwAAAyEI5VcBCr3I/QgAAyEKnmT9CJRg2QqZ6ikLcMZVCYmKaQwW+Bj7qDsJCAADIQv4AkEIAAMhCAADIQgAAyEIAAMhCGqukQmrOhkNLXA9A9kyPQgAAyEIAAMhCClOhQvhtYUIeRG9CasyjQpVSpEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"
61
  },
62
  "_last_episode_starts": {
63
  ":type:": "<class 'numpy.ndarray'>",
@@ -70,7 +70,7 @@
70
  "_current_progress_remaining": -0.0649599999999999,
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'>",
 
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 0x7f01260e52d0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f01260e5360>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f01260e53f0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f01260e5480>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f01260e5510>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f01260e55a0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f01260e5630>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f01260e56c0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f01260e5750>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f01260e57e0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f01260e5870>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f01260e5900>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f01263cb580>"
21
  },
22
  "verbose": true,
23
  "policy_kwargs": {},
 
48
  "_num_timesteps_at_start": 0,
49
  "seed": null,
50
  "action_noise": null,
51
+ "start_time": 1681853518800670751,
52
  "learning_rate": 0.0003,
53
  "tensorboard_log": null,
54
  "lr_schedule": {
 
57
  },
58
  "_last_obs": {
59
  ":type:": "<class 'numpy.ndarray'>",
60
+ ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAL/YZ0OoGvM/swhFQXFMZULOyZpCAADIQpXQkUIAAMhCoGiIQQAAyEJ6ZmlDZ8CJv7iqS0IAAMhCd0sSQvXqCULRnkZC5QuZQgAAyEIAAMhCo56HQ3u4GsAAAMhCAADIQkmOiUIAAMhCju+EQh4bd0JsAFdCAADIQpEheEMruc4+d6ZNQtdiNkKgmXVC1RuEQgAAyEIAAMhCxLhtQgAAyEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"
61
  },
62
  "_last_episode_starts": {
63
  ":type:": "<class 'numpy.ndarray'>",
 
70
  "_current_progress_remaining": -0.0649599999999999,
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'>",
BC-from-behavior-cloning/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b44e43d3888af5899d55b478bf1770d6aacb84b4f20e57f04e96fc370dd7d81f
3
  size 18973
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d90b43630582e04fbe5c38284abbd00e2bbbaf81b9689786c7a886b8f37c5e
3
  size 18973
BC-from-behavior-cloning/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:affa3d3030bf6da6fccf2541fda20047c3b984c50ddfd5646b98b3f242eae4e5
3
  size 9295
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc754462ec6de1ddcb84b5fb50b06eb1191e36d8f9bf66a85829305c063481c5
3
  size 9295
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: RoombaAToB-from-behavior-cloning
17
  metrics:
18
  - type: mean_reward
19
- value: -4967.25 +/- 0.00
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: RoombaAToB-from-behavior-cloning
17
  metrics:
18
  - type: mean_reward
19
+ value: -118.04 +/- 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 0x7fa28a2f12d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa28a2f1360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa28a2f13f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa28a2f1480>", "_build": "<function ActorCriticPolicy._build at 0x7fa28a2f1510>", "forward": "<function ActorCriticPolicy.forward at 0x7fa28a2f15a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa28a2f1630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa28a2f16c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa28a2f1750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa28a2f17e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa28a2f1870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa28a2f1900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa28a2de8c0>"}, "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": 106496, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681848321440440409, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAADHwh0Ooh6+/AADIQgAAyEIGD+9BAADIQnuGHEJ0LOBBZL/nQQAAyEK1u3BD6m8pwAAAyEI5VcBCr3I/QgAAyEKnmT9CJRg2QqZ6ikLcMZVCYmKaQwW+Bj7qDsJCAADIQv4AkEIAAMhCAADIQgAAyEIAAMhCGqukQmrOhkNLXA9A9kyPQgAAyEIAAMhCClOhQvhtYUIeRG9CasyjQpVSpEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.0649599999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 130, "n_steps": 2048, "gamma": 0.999, "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 0x7f01260e52d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f01260e5360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f01260e53f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f01260e5480>", "_build": "<function ActorCriticPolicy._build at 0x7f01260e5510>", "forward": "<function ActorCriticPolicy.forward at 0x7f01260e55a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f01260e5630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f01260e56c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f01260e5750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f01260e57e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f01260e5870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f01260e5900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f01263cb580>"}, "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": 106496, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681853518800670751, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAL/YZ0OoGvM/swhFQXFMZULOyZpCAADIQpXQkUIAAMhCoGiIQQAAyEJ6ZmlDZ8CJv7iqS0IAAMhCd0sSQvXqCULRnkZC5QuZQgAAyEIAAMhCo56HQ3u4GsAAAMhCAADIQkmOiUIAAMhCju+EQh4bd0JsAFdCAADIQpEheEMruc4+d6ZNQtdiNkKgmXVC1RuEQgAAyEIAAMhCxLhtQgAAyEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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": -0.0649599999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 130, "n_steps": 2048, "gamma": 0.999, "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
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -4967.250626935967, "std_reward": 9.094947017729282e-13, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-18T13:12:12.116383"}
 
1
+ {"mean_reward": -118.04484470367439, "std_reward": 1.4210854715202004e-14, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-18T14:39:27.116914"}