Upload best PPO LunarLander-v2 agent (tuned with Optuna).
Browse files- PPO-LunarLander-v2.zip +3 -0
- PPO-LunarLander-v2/_stable_baselines3_version +1 -0
- PPO-LunarLander-v2/data +93 -0
- PPO-LunarLander-v2/policy.optimizer.pth +3 -0
- PPO-LunarLander-v2/policy.pth +3 -0
- PPO-LunarLander-v2/pytorch_variables.pth +3 -0
- PPO-LunarLander-v2/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cbedc3ef315affbd8c8edad8067ad72adbc5e2524cd3d7fb23d43d7571bad65
|
3 |
+
size 146466
|
PPO-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.4.0
|
PPO-LunarLander-v2/data
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x166e740d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x166e74160>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x166e741f0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x166e74280>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x166e74310>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x166e743a0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x166e74430>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x166e744c0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x166e74550>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x166e745e0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x166e74670>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x166da8c40>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=",
|
39 |
+
"n": 4,
|
40 |
+
"shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1032192,
|
46 |
+
"_total_timesteps": 1022258,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1666001117.9894772,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.009717703358643304,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 252,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.9958514574807302,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"target_kl": null
|
93 |
+
}
|
PPO-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0352a2f43a6c4c32631014e079a2a02de50946f46a576f166011e906a056361
|
3 |
+
size 87545
|
PPO-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef2f328cb212027ff485074315949c667fb50c34a553612a49c2fdc676c4022f
|
3 |
+
size 43073
|
PPO-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
PPO-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: macOS-13.0-arm64-arm-64bit Darwin Kernel Version 22.1.0: Sun Oct 2 22:38:57 PDT 2022; root:xnu-8792.41.7~13/RELEASE_ARM64_T6000
|
2 |
+
Python: 3.9.13
|
3 |
+
Stable-Baselines3: 1.4.0
|
4 |
+
PyTorch: 1.12.1
|
5 |
+
GPU Enabled: False
|
6 |
+
Numpy: 1.23.3
|
7 |
+
Gym: 0.19.0
|
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 256.22 +/- 29.66
|
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 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
config.json
ADDED
@@ -0,0 +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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x166e740d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x166e74160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x166e741f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x166e74280>", "_build": "<function ActorCriticPolicy._build at 0x166e74310>", "forward": "<function ActorCriticPolicy.forward at 0x166e743a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x166e74430>", "_predict": "<function ActorCriticPolicy._predict at 0x166e744c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x166e74550>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x166e745e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x166e74670>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x166da8c40>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1032192, "_total_timesteps": 1022258, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1666001117.9894772, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.009717703358643304, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 252, "n_steps": 1024, "gamma": 0.9958514574807302, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "macOS-13.0-arm64-arm-64bit Darwin Kernel Version 22.1.0: Sun Oct 2 22:38:57 PDT 2022; root:xnu-8792.41.7~13/RELEASE_ARM64_T6000", "Python": "3.9.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.1", "GPU Enabled": "False", "Numpy": "1.23.3", "Gym": "0.19.0"}}
|
replay.mp4
ADDED
Binary file (389 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 256.22245209823296, "std_reward": 29.66482374520853, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-10-17T06:23:40.568209"}
|