alperenunlu commited on
Commit
7be737d
·
1 Parent(s): aed4882

Tune Hyperparameters.

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
PPO-LunarLander-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1cb69595c87ca969a36336dd5a1777027fb53e3de3829157742c6a45738a055
3
- size 146754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7ed8ea0228286d6614997a208b67626b08fa760f5efa39e1ae849fda812a63
3
+ size 148052
PPO-LunarLander-v2/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.0.0a5
 
1
+ 2.1.0
PPO-LunarLander-v2/data CHANGED
@@ -4,35 +4,35 @@
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 0x786fba929120>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fba9291b0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fba929240>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fba9292d0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x786fba929360>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x786fba9293f0>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x786fba929480>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fba929510>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x786fba9295a0>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fba929630>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fba9296c0>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x786fba929750>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x786fba91fc80>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
- "num_timesteps": 1015808,
25
- "_total_timesteps": 1000000,
26
  "_num_timesteps_at_start": 0,
27
- "seed": null,
28
  "action_noise": null,
29
- "start_time": 1691417432587568972,
30
- "learning_rate": 0.0003,
31
- "tensorboard_log": null,
32
- "_last_obs": {
33
- ":type:": "<class 'numpy.ndarray'>",
34
- ":serialized:": "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"
35
  },
 
 
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
38
  ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
@@ -41,59 +41,59 @@
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
- "_current_progress_remaining": -0.015808000000000044,
45
  "_stats_window_size": 100,
46
  "ep_info_buffer": {
47
  ":type:": "<class 'collections.deque'>",
48
- ":serialized:": "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"
49
  },
50
  "ep_success_buffer": {
51
  ":type:": "<class 'collections.deque'>",
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
- "_n_updates": 248,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
- ":serialized:": "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",
58
  "dtype": "float32",
59
  "bounded_below": "[ True True True True True True True True]",
60
  "bounded_above": "[ True True True True True True True True]",
61
  "_shape": [
62
  8
63
  ],
64
- "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
65
- "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
66
- "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
67
- "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
68
  "_np_random": null
69
  },
70
  "action_space": {
71
  ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
- ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
73
  "n": "4",
74
  "start": "0",
75
  "_shape": [],
76
  "dtype": "int64",
77
- "_np_random": null
78
  },
79
- "n_envs": 16,
80
- "n_steps": 1024,
81
  "gamma": 0.999,
82
- "gae_lambda": 0.98,
83
- "ent_coef": 0.01,
84
- "vf_coef": 0.5,
85
  "max_grad_norm": 0.5,
86
- "batch_size": 64,
87
- "n_epochs": 4,
88
  "clip_range": {
89
  ":type:": "<class 'function'>",
90
- ":serialized:": "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"
91
  },
92
  "clip_range_vf": null,
93
  "normalize_advantage": true,
94
  "target_kl": null,
95
  "lr_schedule": {
96
  ":type:": "<class 'function'>",
97
- ":serialized:": "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"
98
  }
99
  }
 
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 0x2a0993be0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x2a0993c70>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2a0993d00>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x2a0993d90>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x2a0993e20>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x2a0993eb0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x2a0993f40>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2a0994040>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x2a09940d0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2a0994160>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x2a09941f0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x2a0994280>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x2a098acc0>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
+ "num_timesteps": 2002944,
25
+ "_total_timesteps": 2000000,
26
  "_num_timesteps_at_start": 0,
27
+ "seed": 0,
28
  "action_noise": null,
29
+ "start_time": 1694778628873106000,
30
+ "learning_rate": {
31
+ ":type:": "<class 'function'>",
32
+ ":serialized:": "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"
 
 
33
  },
34
+ "tensorboard_log": null,
35
+ "_last_obs": null,
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
38
  ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
 
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
+ "_current_progress_remaining": -0.0014719999999999178,
45
  "_stats_window_size": 100,
46
  "ep_info_buffer": {
47
  ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "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"
49
  },
50
  "ep_success_buffer": {
51
  ":type:": "<class 'collections.deque'>",
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
+ "_n_updates": 4890,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
+ ":serialized:": "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",
58
  "dtype": "float32",
59
  "bounded_below": "[ True True True True True True True True]",
60
  "bounded_above": "[ True True True True True True True True]",
61
  "_shape": [
62
  8
63
  ],
64
+ "low": "[-1.5 -1.5 -5. -5. -3.1415927 -5.\n -0. -0. ]",
65
+ "high": "[1.5 1.5 5. 5. 3.1415927 5. 1.\n 1. ]",
66
+ "low_repr": "[-1.5 -1.5 -5. -5. -3.1415927 -5.\n -0. -0. ]",
67
+ "high_repr": "[1.5 1.5 5. 5. 3.1415927 5. 1.\n 1. ]",
68
  "_np_random": null
69
  },
70
  "action_space": {
71
  ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
+ ":serialized:": "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",
73
  "n": "4",
74
  "start": "0",
75
  "_shape": [],
76
  "dtype": "int64",
77
+ "_np_random": "Generator(PCG64)"
78
  },
79
+ "n_envs": 1,
80
+ "n_steps": 256,
81
  "gamma": 0.999,
82
+ "gae_lambda": 0.95,
83
+ "ent_coef": 0.0012069732975503813,
84
+ "vf_coef": 0.3326356386659747,
85
  "max_grad_norm": 0.5,
86
+ "batch_size": 8,
87
+ "n_epochs": 10,
88
  "clip_range": {
89
  ":type:": "<class 'function'>",
90
+ ":serialized:": "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"
91
  },
92
  "clip_range_vf": null,
93
  "normalize_advantage": true,
94
  "target_kl": null,
95
  "lr_schedule": {
96
  ":type:": "<class 'function'>",
97
+ ":serialized:": "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"
98
  }
99
  }
PPO-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a676467cbb2859bd2c1fbbe3bfc7ec0724bd9bc232887014b8e4ce4475db83d
3
- size 87929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2f7c7005631cc6686747fd6ef7c3902d0d0faec3f7e81b8233147d4e17c864
3
+ size 87978
PPO-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ea3d2f08d1f80473d5b7691f64e1c2c79930d7a50a126ad2fae2871d55af622
3
- size 43329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06105539a181420809bfe34806e91a74f325431cfe347725f0851ced856ff4d0
3
+ size 43634
PPO-LunarLander-v2/pytorch_variables.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
- size 431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
3
+ size 864
PPO-LunarLander-v2/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
2
  - Python: 3.10.12
3
- - Stable-Baselines3: 2.0.0a5
4
- - PyTorch: 2.0.1+cu118
5
- - GPU Enabled: True
6
- - Numpy: 1.22.4
7
  - Cloudpickle: 2.2.1
8
- - Gymnasium: 0.28.1
9
- - OpenAI Gym: 0.25.2
 
1
+ - OS: macOS-14.0-arm64-arm-64bit Darwin Kernel Version 23.0.0: Thu Aug 17 21:23:05 PDT 2023; root:xnu-10002.1.11~3/RELEASE_ARM64_T6000
2
  - Python: 3.10.12
3
+ - Stable-Baselines3: 2.1.0
4
+ - PyTorch: 2.2.0.dev20230910
5
+ - GPU Enabled: False
6
+ - Numpy: 1.24.3
7
  - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.26.2
README.md CHANGED
@@ -16,30 +16,69 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: 244.16 +/- 18.09
20
  name: mean_reward
21
  verified: false
22
  ---
23
 
24
  # **PPO** Agent playing **LunarLander-v2**
25
  This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
- using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
27
 
28
- ## Usage (with Stable-baselines3)
 
 
29
 
30
- ```python
31
- from stable_baselines3 import PPO
32
- from stable_baselines3.common.monitor import Monitor
33
- from huggingface_sb3 import load_from_hub
 
 
 
 
 
 
 
 
 
 
 
 
34
 
35
- repo_id = "alperenunlu/PPO-LunarLander-v2"
36
- filename = "PPO-LunarLander-v2.zip"
 
 
 
37
 
38
- checkpoint = load_from_hub(repo_id, filename)
39
- model = PPO.load(checkpoint, print_system_info=True)
 
 
 
 
40
 
41
- eval_env = Monitor(gym.make("LunarLander-v2", render_mode="human"))
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
 
43
- mean_rwd, std_rwd = evaluate_policy(model, eval_env, n_eval_episodes=10)
44
- print(f"mean_reward: {mean_rwd}±{std_rwd}")
 
45
  ```
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 280.82 +/- 15.04
20
  name: mean_reward
21
  verified: false
22
  ---
23
 
24
  # **PPO** Agent playing **LunarLander-v2**
25
  This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
27
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
28
 
29
+ The RL Zoo is a training framework for Stable Baselines3
30
+ reinforcement learning agents,
31
+ with hyperparameter optimization and pre-trained agents included.
32
 
33
+ ## Usage (with SB3 RL Zoo)
34
+
35
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
+
39
+ Install the RL Zoo (with SB3 and SB3-Contrib):
40
+ ```bash
41
+ pip install rl_zoo3
42
+ ```
43
+
44
+ ```
45
+ # Download model and save it into the logs/ folder
46
+ python -m rl_zoo3.load_from_hub --algo ppo --env LunarLander-v2 -orga alperenunlu -f logs/
47
+ python -m rl_zoo3.enjoy --algo ppo --env LunarLander-v2 -f logs/
48
+ ```
49
 
50
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
51
+ ```
52
+ python -m rl_zoo3.load_from_hub --algo ppo --env LunarLander-v2 -orga alperenunlu -f logs/
53
+ python -m rl_zoo3.enjoy --algo ppo --env LunarLander-v2 -f logs/
54
+ ```
55
 
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo ppo --env LunarLander-v2 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo ppo --env LunarLander-v2 -f logs/ -orga alperenunlu
61
+ ```
62
 
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 8),
66
+ ('clip_range', 0.2),
67
+ ('ent_coef', 0.0012069732975503813),
68
+ ('gae_lambda', 0.95),
69
+ ('gamma', 0.999),
70
+ ('learning_rate', 0.0004080379698108855),
71
+ ('max_grad_norm', 0.5),
72
+ ('n_envs', 16),
73
+ ('n_epochs', 10),
74
+ ('n_steps', 256),
75
+ ('n_timesteps', 2000000.0),
76
+ ('policy', 'MlpPolicy'),
77
+ ('vf_coef', 0.3326356386659747),
78
+ ('normalize', False)])
79
+ ```
80
 
81
+ # Environment Arguments
82
+ ```python
83
+ {'render_mode': 'rgb_array'}
84
  ```
args.yml ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - ppo
4
+ - - conf_file
5
+ - ppo.yml
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - LunarLander-v2
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 5
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - logs/
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 1
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - -1
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 289296977
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - ''
64
+ - - track
65
+ - false
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - null
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - wandb_tags
81
+ - []
config.yml ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 8
4
+ - - clip_range
5
+ - 0.2
6
+ - - ent_coef
7
+ - 0.0012069732975503813
8
+ - - gae_lambda
9
+ - 0.95
10
+ - - gamma
11
+ - 0.999
12
+ - - learning_rate
13
+ - 0.0004080379698108855
14
+ - - max_grad_norm
15
+ - 0.5
16
+ - - n_envs
17
+ - 16
18
+ - - n_epochs
19
+ - 10
20
+ - - n_steps
21
+ - 256
22
+ - - n_timesteps
23
+ - 2000000.0
24
+ - - policy
25
+ - MlpPolicy
26
+ - - vf_coef
27
+ - 0.3326356386659747
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ render_mode: rgb_array
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 244.15573720000003, "std_reward": 18.08878985884901, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-07T14:41:53.737577"}
 
1
+ {"mean_reward": 280.8177559, "std_reward": 15.041655239559867, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T15:47:56.006682"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27db018580afba1ebc7a7e2eb85239a5bb09b79a875f7520557c7cfc56a4daae
3
+ size 209899