Upload PPO LunarLander-v2 trained agent
Browse files- LunarLander-v2.zip +3 -0
- LunarLander-v2/_stable_baselines3_version +1 -0
- LunarLander-v2/data +99 -0
- LunarLander-v2/policy.optimizer.pth +3 -0
- LunarLander-v2/policy.pth +3 -0
- LunarLander-v2/pytorch_variables.pth +3 -0
- LunarLander-v2/system_info.txt +9 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:309cd5b9938764069d0f17e4b4328e3b1bbd67405dfae20de37f9ed256d25764
|
3 |
+
size 146236
|
LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
LunarLander-v2/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f7376fb4b80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7376fb4c10>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7376fb4ca0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7376fb4d30>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f7376fb4dc0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f7376fb4e50>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7376fb4ee0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7376fb4f70>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f7376fb5000>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7376fb5090>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7376fb5120>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7376fb51b0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f732f74ccc0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1685521553490267826,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_episode_starts": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.015808000000000044,
|
45 |
+
"_stats_window_size": 100,
|
46 |
+
"ep_info_buffer": {
|
47 |
+
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "gAWVPQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHKMbjxTbWWMAWyUTVcBjAF0lEdAll72AoXsPnV9lChoBkdAcbNQgcLjP2gHTTMBaAhHQJZuE6zVtoB1fZQoaAZHQCPKQo1DSgJoB0v3aAhHQJZv+DCgsbx1fZQoaAZHQHGt55u63ApoB00uAWgIR0CWcCFocrAhdX2UKGgGR0BwCBb+tKZlaAdNSwFoCEdAlnCGk8A7xXV9lChoBkdAc0V24d6syWgHS/poCEdAlnYd0q6OHXV9lChoBkdAcRJeZ5Rj0GgHTUYBaAhHQJZ2OwRoRI11fZQoaAZHQHCNvZVXFLpoB007AWgIR0CWdq0kGA09dX2UKGgGR0BwEzdepn6EaAdNLgFoCEdAlnbqBAfMfXV9lChoBkdAcbv5Fw1iv2gHTRQBaAhHQJZ4iRB/qgR1fZQoaAZHQHHfm3nZCfJoB00oAWgIR0CWeJrDqGDddX2UKGgGR0Bxe7FOwgTzaAdNXgFoCEdAlnmNs7+1jXV9lChoBkdAcweK4x1xKmgHTQgBaAhHQJZ5lkBjnV51fZQoaAZHQHDgW43FUAFoB02PAWgIR0CWeaustCiRdX2UKGgGR0BtdFCVrylOaAdNXAFoCEdAlnm/NFBppXV9lChoBkdAbnzDFZPl+2gHTVcBaAhHQJZ6BqYZ2p11fZQoaAZHQEphAaef7JpoB0viaAhHQJZ6paiblRx1fZQoaAZHQHEbtCZ4Oc5oB00iAWgIR0CWfE/xUedTdX2UKGgGR0BwypjG1hLHaAdNMgFoCEdAln0IFFDv3XV9lChoBkdAU5ZjVhCtzWgHS9NoCEdAln8QeA/cFnV9lChoBkdAW8xkMCtA9mgHTegDaAhHQJaAPtD2Jzl1fZQoaAZHQFHlByCFsYVoB0vaaAhHQJaB/o6jnFJ1fZQoaAZHQHF653os7MhoB001AWgIR0CWgsOY6XBydX2UKGgGR0BygI5S3solaAdNQAFoCEdAloNbhJiAlXV9lChoBkdActNIre67NGgHTTcBaAhHQJaDWO5rgwZ1fZQoaAZHQGwACvgWJrNoB00jAWgIR0CWhG5M10kodX2UKGgGR0BwwqIYWLxaaAdNKwFoCEdAloTJudf9gnV9lChoBkdAcIajebd8A2gHTScBaAhHQJaFzTfBN211fZQoaAZHQG/FVcD8tPJoB00rAWgIR0CWhg6InBtUdX2UKGgGR0BxcRpVS4vwaAdNIQFoCEdAlocdv863iXV9lChoBkdAbiy/7iyY5WgHTUEBaAhHQJaH0t8NQTF1fZQoaAZHQGwD5lFtsN5oB01tAWgIR0CWiY+hGpdbdX2UKGgGR0Bs7HWYnfEXaAdNJgFoCEdAlosBPj4pMHV9lChoBkdAb0roOhCdBmgHTUUBaAhHQJaLkuyu6mR1fZQoaAZHQG79O4gA6uJoB00mAWgIR0CWj8sw+MZQdX2UKGgGR0BwCKhoM8YAaAdNTQFoCEdAlpCVzU7SzHV9lChoBkdAcQmYbsF+u2gHTQ8BaAhHQJaSxFLFn7J1fZQoaAZHQHB10tyxRl9oB001AWgIR0CWk2hakhzOdX2UKGgGR0BtxKI7/4qPaAdNLwFoCEdAlpQUt29tdnV9lChoBkdAbvNr/sE7n2gHTUEBaAhHQJaWFWBBiTd1fZQoaAZHQG4tdUS7GvRoB000AWgIR0CWloN9H+ZPdX2UKGgGR0ByQVSFXaJzaAdNOwFoCEdAlpdUK/mDDnV9lChoBkdAcN0nUUfxMGgHTUUBaAhHQJaZK+yquKZ1fZQoaAZHQG8dBF/hESdoB01pAWgIR0CWmoNDtw71dX2UKGgGR0ButuJWNm16aAdNUwFoCEdAlpqhQzk6tHV9lChoBkdAYSu1hsqJ/GgHTegDaAhHQJabNnzxwyZ1fZQoaAZHQHINMKCxu89oB00mAWgIR0CWm9k7fYSQdX2UKGgGR0Bq873M6ij+aAdNTAFoCEdAlpxKV2Rq5HV9lChoBkdAcG+AZ88cMmgHTTEBaAhHQJacsG3WnTB1fZQoaAZHQHHqqI7/4qRoB00WAWgIR0CWrKJFLFn7dX2UKGgGR0BymKsxO+IuaAdNNQFoCEdAlq1hkiD/VHV9lChoBkdATFN+Zw4sE2gHS/ZoCEdAlq1vYraufXV9lChoBkdAcUJgA6uGK2gHTRgBaAhHQJauUTXarWB1fZQoaAZHQG/aOOKfnOloB001AWgIR0CWrwYg7o0RdX2UKGgGR0BGXi0ngHeKaAdNCAFoCEdAlq/6QiiZfHV9lChoBkdAcxDFaB7NS2gHTTsBaAhHQJaxK9mHxjJ1fZQoaAZHQHNMbuYx+KFoB00KAWgIR0CWsVCGvfTDdX2UKGgGR0BugvPJJXhgaAdNOgFoCEdAlrFllXiiqXV9lChoBkdAcnswMpgCwWgHTQUBaAhHQJayZky1uzh1fZQoaAZHQHEZQgkka/BoB0v9aAhHQJazsyLyc1B1fZQoaAZHQHAKudK/VRVoB00lAWgIR0CWtDpZwGW2dX2UKGgGR0ByBW2F36hyaAdNJgFoCEdAlrTd+CsfaHV9lChoBkdAcKDUkfLcK2gHTW0BaAhHQJa2YV1wHZ91fZQoaAZHQHCoMUVSGahoB004AWgIR0CWtm63y7PIdX2UKGgGR0BvsRvWH1vmaAdNFwFoCEdAlrgKa9bosHV9lChoBkdAbaQz4UN8V2gHTUQBaAhHQJa5Dd1uBMB1fZQoaAZHQHLYBYA80UJoB005AWgIR0CWuXO7xusLdX2UKGgGR0BxQdnBciW3aAdNLgFoCEdAlrn5H3Dej3V9lChoBkdAbIpkxREWqWgHTUABaAhHQJa7gQxvegt1fZQoaAZHQHHsVbqyGBZoB00uAWgIR0CWu9fTkQwsdX2UKGgGR0ByhiG47Rv4aAdNGgFoCEdAlrxngYP5HnV9lChoBkdAcGVH6/IsAmgHTScBaAhHQJa8xp7CzkZ1fZQoaAZHQHEXHyy2QXBoB00lAWgIR0CWvewX668QdX2UKGgGR0BxKvAYYR/WaAdNRAFoCEdAlr4PU8V58nV9lChoBkdAb92MKCxu9GgHTSABaAhHQJa/cRlHz6J1fZQoaAZHQG3ukp7TlT5oB009AWgIR0CWwAz67/XHdX2UKGgGR0ByqowlByCGaAdNCAFoCEdAlsCjFdcB2nV9lChoBkdAcbjdaMaS92gHTTIBaAhHQJbAuCmMwUR1fZQoaAZHQGBG+BYmsvJoB03oA2gIR0CWwvZrpJPJdX2UKGgGR0Bvj+bmU4aQaAdNWwFoCEdAlsTyLEUCaXV9lChoBkdAb2H6sQumJmgHTTYBaAhHQJbFU8Tzund1fZQoaAZHQG7BV63RXwNoB007AWgIR0CWxwtQKrq/dX2UKGgGR0BwDl+mWMS9aAdNEQFoCEdAlsgpc5bQkXV9lChoBkdAceapyp71I2gHTRQBaAhHQJbIyJ79hql1fZQoaAZHQHJMKRp1zQxoB01WAWgIR0CWyT2AG0NSdX2UKGgGR0ByZ+SjgydnaAdNLAFoCEdAlssGqT8pC3V9lChoBkdAcHHX7Lt/nWgHTU0BaAhHQJbN5HqeK9B1fZQoaAZHQGvEgB91EE1oB01AAWgIR0CWzydMTN+tdX2UKGgGR0Bv2PtF8XvZaAdNRgFoCEdAls/TGYKIBXV9lChoBkdAcF5dM0xdp2gHTSABaAhHQJbSCyMUAT91fZQoaAZHQHHDMinpB5ZoB01DAWgIR0CW0i8V58jSdX2UKGgGR0BwrSEwnH/+aAdNMAFoCEdAltMvMfRu0nV9lChoBkdAbvU5qdpZfWgHTXMBaAhHQJbWOOdXko51fZQoaAZHQHACEP6KtPpoB00sAWgIR0CW1+CTlkpadX2UKGgGR0ByYIzTF2mpaAdNGQFoCEdAlth2u5jH43V9lChoBkdAceuvZAY51mgHTUoBaAhHQJbZC11GLDR1fZQoaAZHQHBois4ku6FoB00ZAWgIR0CW2dA4GUwBdX2UKGgGR0Bx1QGLUCq7aAdNLgFoCEdAlto/ZIxxk3V9lChoBkdAcpZmZE2HcmgHTQMBaAhHQJbagwj+rEN1fZQoaAZHQG/EIY3vQWxoB02iAWgIR0CW21opx3mndWUu"
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 252,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
98 |
+
}
|
99 |
+
}
|
LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cea3048320008731ba4d3a7172daf332881c3105b6e7bbd3de56e32faaa0dbe
|
3 |
+
size 87545
|
LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8430e46ac285310bbfcaeffbf0b0fc17727d89ca004a3ef86ed6595d8d388f2
|
3 |
+
size 43201
|
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
|
LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
|
2 |
+
- Python: 3.10.11
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
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: 255.97 +/- 17.02
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f7376fb4b80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7376fb4c10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7376fb4ca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7376fb4d30>", "_build": "<function ActorCriticPolicy._build at 0x7f7376fb4dc0>", "forward": "<function ActorCriticPolicy.forward at 0x7f7376fb4e50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7376fb4ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7376fb4f70>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7376fb5000>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7376fb5090>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7376fb5120>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7376fb51b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f732f74ccc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1685521553490267826, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 252, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "False", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
ADDED
Binary file (170 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 255.97319359447857, "std_reward": 17.017050427924097, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-31T08:58:25.342492"}
|