marleyshan21
commited on
Commit
•
b519d6a
1
Parent(s):
5189e1b
First test on PPO - LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 262.02 +/- 17.63
|
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** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
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 0x7fece32239e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fece3223a70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fece3223b00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fece3223b90>", "_build": "<function ActorCriticPolicy._build at 0x7fece3223c20>", "forward": "<function ActorCriticPolicy.forward at 0x7fece3223cb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fece3223d40>", "_predict": "<function ActorCriticPolicy._predict at 0x7fece3223dd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fece3223e60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fece3223ef0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fece3223f80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fece3277510>"}, "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": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651732178.5143795, "learning_rate": 0.0001, "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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 460, "n_steps": 2048, "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": 10, "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:cdd2b3fe8d52c7a85277cd4ec763e885ab692a7cc9468e49e8ae4dbf7830ee36
|
3 |
+
size 144103
|
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:": "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 0x7fece32239e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fece3223a70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fece3223b00>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fece3223b90>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fece3223c20>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fece3223cb0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fece3223d40>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fece3223dd0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fece3223e60>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fece3223ef0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fece3223f80>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fece3277510>"
|
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": 1507328,
|
46 |
+
"_total_timesteps": 1500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651732178.5143795,
|
51 |
+
"learning_rate": 0.0001,
|
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": -0.004885333333333408,
|
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": 460,
|
79 |
+
"n_steps": 2048,
|
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": 10,
|
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 sha256:2605a18d0b21b0da9322a37137aa74192c5b378f7f605e602694c4e6d156c943
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24f2c533d13d0eeab7fdd57f0ef202c9f2cc6ffbe3ec5fe6a17b805fa3e48167
|
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 sha256:8624d7222f5850a2b3ecdf80330e535a0c761ba647c3af3c82a617b89fd2f12f
|
3 |
+
size 223312
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 262.02251020912206, "std_reward": 17.63081131903448, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T08:04:13.123221"}
|