First commit
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -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 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 239.56 +/- 34.98
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f426793e290>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f426793e320>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f426793e3b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f426793e440>", "_build": "<function ActorCriticPolicy._build at 0x7f426793e4d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f426793e560>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f426793e5f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f426793e680>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f426793e710>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f426793e7a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f426793e830>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f42679941e0>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653236127.912338, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "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 sha256:7f5d88b42318a36d03bfdab1fa324cf4c4321911dfff364f024570b667f7cb30
|
3 |
+
size 144155
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f426793e290>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f426793e320>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f426793e3b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f426793e440>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f426793e4d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f426793e560>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f426793e5f0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f426793e680>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f426793e710>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f426793e7a0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f426793e830>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f42679941e0>"
|
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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653236127.912338,
|
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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10100478b8f847603cce3baa83f8072659575b3fd08e7bd23d0225461d690889
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d0714b730a4fe51a8684a3ff1951085d0c33091cba272bb2c5b6a1c76c39e15
|
3 |
+
size 43201
|
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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b172be7acfd69b6f4f48dc44929c75457764e496e0de063741ca8622643ce5be
|
3 |
+
size 254113
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 239.5622256275023, "std_reward": 34.979574741959674, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-22T16:32:21.357733"}
|