Upload first PPO LunarLander-v2 trained agent, reward = 260+/-19
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: 248.23 +/- 24.73
|
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:": "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 0x7f932ab17950>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f932ab179e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f932ab17a70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f932ab17b00>", "_build": "<function ActorCriticPolicy._build at 0x7f932ab17b90>", "forward": "<function ActorCriticPolicy.forward at 0x7f932ab17c20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f932ab17cb0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f932ab17d40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f932ab17dd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f932ab17e60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f932ab17ef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f932aaec630>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651998700.41488, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gASVXwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX2ZpbGxfZnVuY3Rpb26Uk5QoaACMD19tYWtlX3NrZWxfZnVuY5STlGgAjA1fYnVpbHRpbl90eXBllJOUjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlEsBfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdYeUUpR9lCiMB2dsb2JhbHOUfZSMCGRlZmF1bHRzlE6MBGRpY3SUfZSMDmNsb3N1cmVfdmFsdWVzlF2URz8zqSowVTJhYYwGbW9kdWxllGgZjARuYW1llGgPjANkb2OUTowXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC2Fubm90YXRpb25zlH2UjAhxdWFsbmFtZZSMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjAprd2RlZmF1bHRzlE51dFIu"}, "_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 sha256:9d4c98d2ee83da88e3a1d94f4103bac11efc31f359643fc1bedb7a0b023b144e
|
3 |
+
size 143856
|
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 0x7f932ab17950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f932ab179e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f932ab17a70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f932ab17b00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f932ab17b90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f932ab17c20>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f932ab17cb0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f932ab17d40>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f932ab17dd0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f932ab17e60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f932ab17ef0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f932aaec630>"
|
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": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651998700.41488,
|
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:e956560bf989c72940cdfc4196f97407a0760ba9c315afb9b64bb806a80bb47c
|
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:ea35d40c0e40b9392bd3a4b01b85ee5845f3a833210429980d339564004fd20e
|
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 sha256:5947c1379a4ffc73714878b34ede480963723060b457b14a8a2632a70bd813f9
|
3 |
+
size 253318
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 248.22957189639834, "std_reward": 24.727764110838866, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T08:58:49.357339"}
|