first model training using PPO
Browse files- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- rlAgentForTraining(ppo-LUnarLander-v2).zip +3 -0
- rlAgentForTraining(ppo-LUnarLander-v2)/_stable_baselines3_version +1 -0
- rlAgentForTraining(ppo-LUnarLander-v2)/data +94 -0
- rlAgentForTraining(ppo-LUnarLander-v2)/policy.optimizer.pth +3 -0
- rlAgentForTraining(ppo-LUnarLander-v2)/policy.pth +3 -0
- rlAgentForTraining(ppo-LUnarLander-v2)/pytorch_variables.pth +3 -0
- rlAgentForTraining(ppo-LUnarLander-v2)/system_info.txt +7 -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: 243.23 +/- 24.88
|
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 0x7f20ae939ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f20ae939f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f20ae93f040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f20ae93f0d0>", "_build": "<function ActorCriticPolicy._build at 0x7f20ae93f160>", "forward": "<function ActorCriticPolicy.forward at 0x7f20ae93f1f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f20ae93f280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f20ae93f310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f20ae93f3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f20ae93f430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f20ae93f4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f20ae93c180>"}, "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": 1670648226366671897, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (232 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 243.22743980605702, "std_reward": 24.876900580230856, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T05:26:00.720449"}
|
rlAgentForTraining(ppo-LUnarLander-v2).zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa317fe9deb26fab1619df2e9a73af7adb891e23d4c46650e5eb71f97ecb0f2c
|
3 |
+
size 147214
|
rlAgentForTraining(ppo-LUnarLander-v2)/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
rlAgentForTraining(ppo-LUnarLander-v2)/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f20ae939ee0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f20ae939f70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f20ae93f040>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f20ae93f0d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f20ae93f160>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f20ae93f1f0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f20ae93f280>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f20ae93f310>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f20ae93f3a0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f20ae93f430>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f20ae93f4c0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f20ae93c180>"
|
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:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1670648226366671897,
|
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": -0.015808000000000044,
|
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": 248,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
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 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
rlAgentForTraining(ppo-LUnarLander-v2)/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d0bbe8126d9515cd9e0637fa52186ce282c7851a6963cb5b6b5a4a7ad71d836
|
3 |
+
size 87929
|
rlAgentForTraining(ppo-LUnarLander-v2)/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:537218d76be0d4d308dd7647d119c2b46d77fcb326bfd5e5d0a17f82a58a6f0d
|
3 |
+
size 43201
|
rlAgentForTraining(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
|
rlAgentForTraining(ppo-LUnarLander-v2)/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|