morganjeffries
commited on
Commit
·
bf21505
1
Parent(s):
13d6bfc
Upload PPO LunarLander-v2 trained agent
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: 259.15 +/- 17.26
|
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 0x7f7d61e7c550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7d61e7c5e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7d61e7c670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7d61e7c700>", "_build": "<function ActorCriticPolicy._build at 0x7f7d61e7c790>", "forward": "<function ActorCriticPolicy.forward at 0x7f7d61e7c820>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7d61e7c8b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7d61e7c940>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7d61e7c9d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7d61e7ca60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7d61e7caf0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7d61e7cb80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7d61ef8270>"}, "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": 1676833647809032947, "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 sha256:75513ad27bdbe98c5469d5a81101c0f751a282e7afee3bef2ea7ae1f1ae6036c
|
3 |
+
size 147420
|
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 0x7f7d61e7c550>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7d61e7c5e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7d61e7c670>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7d61e7c700>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f7d61e7c790>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f7d61e7c820>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7d61e7c8b0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7d61e7c940>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f7d61e7c9d0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7d61e7ca60>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7d61e7caf0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7d61e7cb80>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f7d61ef8270>"
|
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": 1676833647809032947,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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:": "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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:c31c0c9345424c1e52ad543adabeca6d5d7f8a3caf44e5cd3717aa00bd96129c
|
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:a6aaaf6afe5b0e515288f14b8438c6ddd20df0546c98b9029dc19b24b00bf11f
|
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 (222 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 259.15353612333337, "std_reward": 17.256083912299637, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-19T19:32:25.443811"}
|