unit1_test
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: 254.84 +/- 24.38
|
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 0x7f93c7801280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f93c7801310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f93c78013a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f93c7801430>", "_build": "<function ActorCriticPolicy._build at 0x7f93c78014c0>", "forward": "<function ActorCriticPolicy.forward at 0x7f93c7801550>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f93c78015e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f93c7801670>", "_predict": "<function ActorCriticPolicy._predict at 0x7f93c7801700>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f93c7801790>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f93c7801820>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f93c78018b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f93c77fa9f0>"}, "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:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1675565659963479522, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "n_steps": 1024, "gamma": 0.999, "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, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ecfa20dda9530fcf4387adfdca40a3ee8755323b54fa357c372ea9cff1666f9
|
3 |
+
size 147424
|
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 0x7f93c7801280>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f93c7801310>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f93c78013a0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f93c7801430>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f93c78014c0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f93c7801550>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f93c78015e0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f93c7801670>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f93c7801700>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f93c7801790>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f93c7801820>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f93c78018b0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f93c77fa9f0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
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": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1675565659963479522,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
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": 248,
|
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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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 sha256:6de8b1c40242305d4a9b46cf80881ee7d6050c8c20958c2ad2114fe2f9d6f97c
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b517144fe09a452f9e346e5c4d22e3e5da8372448f5971ec468c8f925510211
|
3 |
+
size 43393
|
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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.21.6
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (226 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 254.83574683803445, "std_reward": 24.381115731011423, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-05T03:21:52.650839"}
|