Upload PPO LunarLander-v2 trained agent hyperparameter tunning by optuna
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +95 -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
- replay.mp4 +0 -0
- results.json +1 -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: -856.19 +/- 384.34
|
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 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 0x7fd2497d8790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd2497d8820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd2497d88b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd2497d8940>", "_build": "<function ActorCriticPolicy._build at 0x7fd2497d89d0>", "forward": "<function ActorCriticPolicy.forward at 0x7fd2497d8a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd2497d8af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd2497d8b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd2497d8c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd2497d8ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd2497d8d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd2497d8dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd2497d71b0>"}, "verbose": 0, "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:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677473265517278406, "learning_rate": 0.0358441622999966, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALNuOL0Ep9tAjUKmv8zQO0AUQx8/2ws6PgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3200000, "n_steps": 5, "gamma": 0.8043961479341653, "gae_lambda": 0.8899866602953548, "ent_coef": 0.03652736951434276, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 16, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.0-107-generic-x86_64-with-glibc2.27 # 121~18.04.1-Ubuntu SMP Thu Mar 24 17:21:33 UTC 2022", "Python": "3.8.0", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "False", "Numpy": "1.24.1", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f632c9aaf490943667579112bf579e29607ada59e6c4158461eae0a0e39406b4
|
3 |
+
size 146223
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 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 0x7fd2497d8790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd2497d8820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd2497d88b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd2497d8940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fd2497d89d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fd2497d8a60>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd2497d8af0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd2497d8b80>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fd2497d8c10>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd2497d8ca0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd2497d8d30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd2497d8dc0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7fd2497d71b0>"
|
21 |
+
},
|
22 |
+
"verbose": 0,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
+
"dtype": "float32",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 1,
|
46 |
+
"num_timesteps": 1000000,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1677473265517278406,
|
52 |
+
"learning_rate": 0.0358441622999966,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "gAWV0QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMTy9ob21lL3N2bWMvLmxvY2FsL2xpYi9weXRob24zLjgvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuCQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjE8vaG9tZS9zdm1jLy5sb2NhbC9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz+iWiqBqXkJhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALNuOL0Ep9tAjUKmv8zQO0AUQx8/2ws6PgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": 0.0,
|
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'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 3200000,
|
80 |
+
"n_steps": 5,
|
81 |
+
"gamma": 0.8043961479341653,
|
82 |
+
"gae_lambda": 0.8899866602953548,
|
83 |
+
"ent_coef": 0.03652736951434276,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 128,
|
87 |
+
"n_epochs": 16,
|
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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a28419c7d5bcdd45f4a74da9c14ccda00927d5535a27e1b818b03d9f1b902e6b
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8894462d5911ac04336f30930b17722ba920ba340fe97aa4f57350ad3d282cc5
|
3 |
+
size 43265
|
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: Linux-5.4.0-107-generic-x86_64-with-glibc2.27 # 121~18.04.1-Ubuntu SMP Thu Mar 24 17:21:33 UTC 2022
|
2 |
+
- Python: 3.8.0
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu117
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.24.1
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (119 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -856.1900397393795, "std_reward": 384.340459532218, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:38:41.418759"}
|