alperenunlu
commited on
Commit
·
7be737d
1
Parent(s):
aed4882
Tune Hyperparameters.
Browse files- .gitattributes +1 -0
- PPO-LunarLander-v2.zip +2 -2
- PPO-LunarLander-v2/_stable_baselines3_version +1 -1
- PPO-LunarLander-v2/data +41 -41
- PPO-LunarLander-v2/policy.optimizer.pth +2 -2
- PPO-LunarLander-v2/policy.pth +2 -2
- PPO-LunarLander-v2/pytorch_variables.pth +2 -2
- PPO-LunarLander-v2/system_info.txt +7 -7
- README.md +53 -14
- args.yml +81 -0
- config.yml +27 -0
- env_kwargs.yml +1 -0
- replay.mp4 +0 -0
- results.json +1 -1
- train_eval_metrics.zip +3 -0
.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:
|
3 |
-
size
|
|
|
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
|
|
|
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
|
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": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
-
"seed":
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
-
"learning_rate":
|
31 |
-
|
32 |
-
|
33 |
-
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAA3HFD5SCuW7pt2Lu4EDCDqz/y+9q6bZOgAAAAAAAIA/gHlXPSl4ILrgsJC3s792sgOPXLv6O6o2AACAPwAAgD8Y3Ja+XYIgP8qa3j0sALC+bUVEvk2JXT4AAAAAAAAAAJrfTj1wt5g/mYqkPdfSgr6dsuk9BhuZvQAAAAAAAAAAIDEZvnvOwD2Lld89GdWSvphogDtTdiy8AAAAAAAAAAAzYZm8j7Izur4v1boH7QG2fa/3OjK4/DkAAIA/AACAPzNzg7nOUaQ/KJJiPM5Mjr4yq1U9Vt2pPQAAAAAAAAAA2kN2Ps64OD+62OW9UQyNvi4WnT2fisS8AAAAAAAAAACAPjE94ZyNunywtLuv09I3QAyIOtEJI7cAAIA/AACAPzPDDb0ONaM/hJy9vaHFtr6mGLW83zUMPQAAAAAAAAAA2oeLvfZEK7pOJ3G5cYMmtMMJgLpIEYs4AACAPwAAgD+zQTE94YyXutvv67rrTB220t49un60BzoAAIA/AACAP5qNk7tI75S6AtUqOVAdKbWEBJ46XMc4tAAAgD8AAIA/M+DPvK6tq7oOHc87pa7NN1Ezkzq4eHo2AACAPwAAgD/NDMc8KXBPulasTTua2asyQqoPuS2scroAAIA/AACAP2ZAq7yk50Q/4WnHvXvmj76l4wy9mzrxPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
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.
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
-
":serialized:": "
|
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": "[-
|
65 |
-
"high": "[
|
66 |
-
"low_repr": "[-
|
67 |
-
"high_repr": "[
|
68 |
"_np_random": null
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
76 |
"dtype": "int64",
|
77 |
-
"_np_random":
|
78 |
},
|
79 |
-
"n_envs":
|
80 |
-
"n_steps":
|
81 |
"gamma": 0.999,
|
82 |
-
"gae_lambda": 0.
|
83 |
-
"ent_coef": 0.
|
84 |
-
"vf_coef": 0.
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
-
":serialized:": "
|
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:
|
3 |
-
size
|
|
|
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:
|
3 |
-
size
|
|
|
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:
|
3 |
-
size
|
|
|
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:
|
2 |
- Python: 3.10.12
|
3 |
-
- Stable-Baselines3: 2.0
|
4 |
-
- PyTorch: 2.0.
|
5 |
-
- GPU Enabled:
|
6 |
-
- Numpy: 1.
|
7 |
- Cloudpickle: 2.2.1
|
8 |
-
- Gymnasium: 0.
|
9 |
-
- OpenAI Gym: 0.
|
|
|
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:
|
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 |
-
|
|
|
|
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
|
35 |
-
|
36 |
-
|
|
|
|
|
|
|
37 |
|
38 |
-
|
39 |
-
|
|
|
|
|
|
|
|
|
40 |
|
41 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
-
|
44 |
-
|
|
|
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":
|
|
|
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
|