davidrd123
commited on
Commit
•
8f2f6f4
1
Parent(s):
5893168
Upload PPO LunarLander-v2 trained agent, 1st try, 1000000 steps
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- ppo-LunarLander-v2b.zip +3 -0
- ppo-LunarLander-v2b/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2b/data +94 -0
- ppo-LunarLander-v2b/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2b/policy.pth +3 -0
- ppo-LunarLander-v2b/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2b/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: -720.16 +/- 564.98
|
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** 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 0x7f973d235dd0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f973d235e60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f973d235ef0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f973d235f80>", "_build": "<function ActorCriticPolicy._build at 0x7f973d23c050>", "forward": "<function ActorCriticPolicy.forward at 0x7f973d23c0e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f973d23c170>", "_predict": "<function ActorCriticPolicy._predict at 0x7f973d23c200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f973d23c290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f973d23c320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f973d23c3b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f973d27bd20>"}, "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": 16384, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651964608.5074828, "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": -0.6384000000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "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-v2b.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb3a1fcb2b84dd2fa193c1d0a480ea7ed2d36f81d3b1a85244cb156f49829eb9
|
3 |
+
size 143910
|
ppo-LunarLander-v2b/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2b/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 0x7f973d235dd0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f973d235e60>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f973d235ef0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f973d235f80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f973d23c050>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f973d23c0e0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f973d23c170>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f973d23c200>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f973d23c290>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f973d23c320>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f973d23c3b0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f973d27bd20>"
|
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": 16384,
|
46 |
+
"_total_timesteps": 10000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651964608.5074828,
|
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": -0.6384000000000001,
|
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": 4,
|
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-v2b/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:593e26d03b8179a6f300f275f1bf8c8f6e25c237a5278d0e94843af67a8d6788
|
3 |
+
size 84829
|
ppo-LunarLander-v2b/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa5d2d33e50e49296c65ae02c0c22170045337c8e48671faeb5a8d52cede0fd9
|
3 |
+
size 43201
|
ppo-LunarLander-v2b/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-v2b/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 sha256:636dfd665456128992e65cf7500f8f9f966e7815a63a048e707b25641b8f928e
|
3 |
+
size 125847
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -720.1645960172639, "std_reward": 564.9848304765812, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T23:04:42.179422"}
|