Upload 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 +108 -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: 203.89 +/- 88.13
|
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 0x7f3263d22ef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3263d22f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3263d25050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3263d250e0>", "_build": "<function ActorCriticPolicy._build at 0x7f3263d25170>", "forward": "<function ActorCriticPolicy.forward at 0x7f3263d25200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3263d25290>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3263d25320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3263d253b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3263d25440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3263d254d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3263d70a50>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVYQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChLgEuAfZSMAnZmlF2UKE0AAU0AAWVzZXUu", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": [128, 128, {"vf": [256, 256]}]}, "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": 1652207107.831144, "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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "n_steps": 1024, "gamma": 0.997, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "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 sha256:39200e9d5436d5a1c63f7d26daf711a52f38e9febdac3efeecbce6a757de6168
|
3 |
+
size 1433986
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f3263d22ef0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3263d22f80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3263d25050>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3263d250e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3263d25170>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3263d25200>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3263d25290>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3263d25320>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3263d253b0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3263d25440>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3263d254d0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f3263d70a50>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {
|
23 |
+
":type:": "<class 'dict'>",
|
24 |
+
":serialized:": "gAWVYQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChLgEuAfZSMAnZmlF2UKE0AAU0AAWVzZXUu",
|
25 |
+
"activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
|
26 |
+
"net_arch": [
|
27 |
+
128,
|
28 |
+
128,
|
29 |
+
{
|
30 |
+
"vf": [
|
31 |
+
256,
|
32 |
+
256
|
33 |
+
]
|
34 |
+
}
|
35 |
+
]
|
36 |
+
},
|
37 |
+
"observation_space": {
|
38 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
39 |
+
":serialized:": "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",
|
40 |
+
"dtype": "float32",
|
41 |
+
"_shape": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
45 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
46 |
+
"bounded_below": "[False False False False False False False False]",
|
47 |
+
"bounded_above": "[False False False False False False False False]",
|
48 |
+
"_np_random": null
|
49 |
+
},
|
50 |
+
"action_space": {
|
51 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
52 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
53 |
+
"n": 4,
|
54 |
+
"_shape": [],
|
55 |
+
"dtype": "int64",
|
56 |
+
"_np_random": null
|
57 |
+
},
|
58 |
+
"n_envs": 16,
|
59 |
+
"num_timesteps": 1507328,
|
60 |
+
"_total_timesteps": 1500000,
|
61 |
+
"_num_timesteps_at_start": 0,
|
62 |
+
"seed": null,
|
63 |
+
"action_noise": null,
|
64 |
+
"start_time": 1652207107.831144,
|
65 |
+
"learning_rate": 0.0003,
|
66 |
+
"tensorboard_log": null,
|
67 |
+
"lr_schedule": {
|
68 |
+
":type:": "<class 'function'>",
|
69 |
+
":serialized:": "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"
|
70 |
+
},
|
71 |
+
"_last_obs": {
|
72 |
+
":type:": "<class 'numpy.ndarray'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"_last_episode_starts": {
|
76 |
+
":type:": "<class 'numpy.ndarray'>",
|
77 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
78 |
+
},
|
79 |
+
"_last_original_obs": null,
|
80 |
+
"_episode_num": 0,
|
81 |
+
"use_sde": false,
|
82 |
+
"sde_sample_freq": -1,
|
83 |
+
"_current_progress_remaining": -0.004885333333333408,
|
84 |
+
"ep_info_buffer": {
|
85 |
+
":type:": "<class 'collections.deque'>",
|
86 |
+
":serialized:": "gAWVThAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIT8x6MZRuY0CUhpRSlIwBbJRN6AOMAXSUR0CgnokKu0TldX2UKGgGaAloD0MIwVd06zUJOkCUhpRSlGgVS4NoFkdAoKB30se4kXV9lChoBmgJaA9DCC6M9KJ2I0ZAlIaUUpRoFUuAaBZHQKChdAsTWXl1fZQoaAZoCWgPQwi+pZwv9o5cQJSGlFKUaBVN6ANoFkdAoKIyTjebeHV9lChoBmgJaA9DCKMgeHx7fyPAlIaUUpRoFUuJaBZHQKCiS7voePt1fZQoaAZoCWgPQwiWPQlszrdKQJSGlFKUaBVLfWgWR0CgpPnQ6ZH/dX2UKGgGaAloD0MI2SeAYmQtY0CUhpRSlGgVTegDaBZHQKClqE2YOUd1fZQoaAZoCWgPQwjb/L/qSEpkQJSGlFKUaBVN6ANoFkdAoKalqagElnV9lChoBmgJaA9DCGy0HOihxiJAlIaUUpRoFUupaBZHQKCnF/XGwRp1fZQoaAZoCWgPQwhZT62+ugIsQJSGlFKUaBVLkWgWR0CgqSlI3BHkdX2UKGgGaAloD0MIIsfWM4QrSECUhpRSlGgVS5FoFkdAoL5G9rXUY3V9lChoBmgJaA9DCAVtcvgkkmZAlIaUUpRoFU3oA2gWR0Cgvq3FtKqXdX2UKGgGaAloD0MIL00R4PRtXUCUhpRSlGgVTegDaBZHQKC/AZ3LV4J1fZQoaAZoCWgPQwjAP6VKlJRmQJSGlFKUaBVN6ANoFkdAoL+0wL3K0XV9lChoBmgJaA9DCKW+LO3U3BpAlIaUUpRoFUt1aBZHQKDBd57gKnh1fZQoaAZoCWgPQwjXFMjsLPryP5SGlFKUaBVLcGgWR0CgwrNvn8sMdX2UKGgGaAloD0MIGuCCbNm5Y0CUhpRSlGgVTegDaBZHQKDC0hyKekJ1fZQoaAZoCWgPQwhSfHxCdi5hQJSGlFKUaBVN6ANoFkdAoMPuitaIN3V9lChoBmgJaA9DCMIXJlMFEUtAlIaUUpRoFUvIaBZHQKDEHbdJrcl1fZQoaAZoCWgPQwhk6NhBJTRFQJSGlFKUaBVN6ANoFkdAoMTxsCT2WnV9lChoBmgJaA9DCG3n+6nxCWVAlIaUUpRoFU3oA2gWR0CgxPQIt16mdX2UKGgGaAloD0MIHNMTlnh0PkCUhpRSlGgVS3poFkdAoMXPd69kBnV9lChoBmgJaA9DCLhc/dikvmRAlIaUUpRoFU3oA2gWR0CgxsxYigTRdX2UKGgGaAloD0MIgT/8/Pe4PECUhpRSlGgVS3loFkdAoMb1ycTakHV9lChoBmgJaA9DCH8zMV2IYUlAlIaUUpRoFUtmaBZHQKDHPId2gWd1fZQoaAZoCWgPQwhKlpNQ+upHQJSGlFKUaBVLjGgWR0Cgxz1P3ztkdX2UKGgGaAloD0MIHLRXHw/QYkCUhpRSlGgVTegDaBZHQKDIvrKvFFV1fZQoaAZoCWgPQwiT36KTpeI4QJSGlFKUaBVLWmgWR0CgyOJQ+EAYdX2UKGgGaAloD0MIbZBJRs7OPECUhpRSlGgVS8toFkdAoMmTfP5YYHV9lChoBmgJaA9DCI16iEZ3bkpAlIaUUpRoFUtyaBZHQKDJmNNJvpB1fZQoaAZoCWgPQwh5O8JpwSc0QJSGlFKUaBVLh2gWR0CgylfVI7NjdX2UKGgGaAloD0MIsdzSakgOZECUhpRSlGgVTegDaBZHQKDLRy1/lQx1fZQoaAZoCWgPQwi1F9F2TE9OQJSGlFKUaBVLXGgWR0Cgy7QfIS13dX2UKGgGaAloD0MIW5TZIJPYQkCUhpRSlGgVS6RoFkdAoMyK8an753V9lChoBmgJaA9DCOYg6GhVB0lAlIaUUpRoFUvOaBZHQKDNuC4jKPp1fZQoaAZoCWgPQwhMjGX6JTYzQJSGlFKUaBVLc2gWR0CgzgP7WNFSdX2UKGgGaAloD0MIF/Ayw8YvYkCUhpRSlGgVTegDaBZHQKDOF/Pw/gR1fZQoaAZoCWgPQwgpBd1e0uhHQJSGlFKUaBVLnWgWR0Cgzhi4rjHXdX2UKGgGaAloD0MIWg2JeywGWUCUhpRSlGgVTegDaBZHQKDPiOxSpBJ1fZQoaAZoCWgPQwgB+n3/5kk+QJSGlFKUaBVLbGgWR0Cg0Ir56+nJdX2UKGgGaAloD0MInz4Cf/g5IcCUhpRSlGgVS3poFkdAoNDyF7D2rXV9lChoBmgJaA9DCM5sV+iDJ0VAlIaUUpRoFUtmaBZHQKDSAbPQfIV1fZQoaAZoCWgPQwgi4uZUMl9hQJSGlFKUaBVN6ANoFkdAoNKF1jiGWXV9lChoBmgJaA9DCLq7zob8TzhAlIaUUpRoFUtmaBZHQKDTId6LOzJ1fZQoaAZoCWgPQwhxqrUwC/BnQJSGlFKUaBVN6ANoFkdAoNPcV1wHaHV9lChoBmgJaA9DCMOdCyO9FE5AlIaUUpRoFUt9aBZHQKDUOu6mO2l1fZQoaAZoCWgPQwhbfAqA8c9jQJSGlFKUaBVN6ANoFkdAoNW1L127nXV9lChoBmgJaA9DCKwCtRg8HD1AlIaUUpRoFUtiaBZHQKDWwaUA1el1fZQoaAZoCWgPQwhXdsHgmn8/QJSGlFKUaBVLcWgWR0Cg1soZAIIGdX2UKGgGaAloD0MIGxNiLqkJYUCUhpRSlGgVTegDaBZHQKDrnhXr+o91fZQoaAZoCWgPQwgMk6mCUf0+QJSGlFKUaBVLZ2gWR0Cg7V6Pjn3ddX2UKGgGaAloD0MImN9pMuMtY0CUhpRSlGgVTegDaBZHQKDuQIKtxMp1fZQoaAZoCWgPQwjJIeLm1BFlQJSGlFKUaBVN6ANoFkdAoO+XMY/FBXV9lChoBmgJaA9DCMQLIlLToEhAlIaUUpRoFUu/aBZHQKDy4hN/OMV1fZQoaAZoCWgPQwhWfhmMEQ5QQJSGlFKUaBVLpWgWR0Cg8wPK2a2GdX2UKGgGaAloD0MIWvENhU8rZkCUhpRSlGgVTegDaBZHQKDzE8fV7Qd1fZQoaAZoCWgPQwicqKW5FWINQJSGlFKUaBVLjmgWR0Cg88ajesPrdX2UKGgGaAloD0MIpdsSueBWZUCUhpRSlGgVTegDaBZHQKD057Y02tN1fZQoaAZoCWgPQwgxCKwcWtwkQJSGlFKUaBVLimgWR0Cg9xbMPjGUdX2UKGgGaAloD0MImtL6WwIoOkCUhpRSlGgVS5BoFkdAoPc5q/M4cXV9lChoBmgJaA9DCAsm/ijq1WJAlIaUUpRoFU3oA2gWR0Cg995mI0qIdX2UKGgGaAloD0MIzEOmfAgVX0CUhpRSlGgVTegDaBZHQKD6iF7D2rZ1fZQoaAZoCWgPQwgUkzfAzGFkQJSGlFKUaBVN6ANoFkdAoPuXVsk6cXV9lChoBmgJaA9DCP6cgvzsE2JAlIaUUpRoFU3oA2gWR0Cg/QRAB1cMdX2UKGgGaAloD0MIbolccAZZZUCUhpRSlGgVTegDaBZHQKD9bKDCgsd1fZQoaAZoCWgPQwgt7dRcblgrQJSGlFKUaBVLeWgWR0Cg/f4EnssydX2UKGgGaAloD0MIKUAUzJiiM0CUhpRSlGgVS45oFkdAoQGCbH6uXHV9lChoBmgJaA9DCMx6MZQTM0dAlIaUUpRoFUueaBZHQKEBif9xZMd1fZQoaAZoCWgPQwg9CtejcB9gQJSGlFKUaBVN6ANoFkdAoQIYHxBmgHV9lChoBmgJaA9DCKbuyi6YDGRAlIaUUpRoFU3oA2gWR0ChAqdb5dnkdX2UKGgGaAloD0MIKQge3146Y0CUhpRSlGgVTegDaBZHQKEDRw2ETQF1fZQoaAZoCWgPQwhtOgK4WeZFQJSGlFKUaBVLamgWR0ChBFtu+AVgdX2UKGgGaAloD0MIQ48YPbfIIMCUhpRSlGgVS4RoFkdAoQUFqrR0EHV9lChoBmgJaA9DCHYZ/tMNVkZAlIaUUpRoFUt2aBZHQKEFNY8uBc11fZQoaAZoCWgPQwjaklUR7o1kQJSGlFKUaBVN6ANoFkdAoQXaNVBD5XV9lChoBmgJaA9DCD6V056S9zRAlIaUUpRoFUuYaBZHQKEGo2hIvrZ1fZQoaAZoCWgPQwgk8Ief/9ZVQJSGlFKUaBVN6ANoFkdAoQborrgO0HV9lChoBmgJaA9DCAuZK4Nqo1BAlIaUUpRoFUtlaBZHQKEHCGoJiRZ1fZQoaAZoCWgPQwjnGmZoPM1qwJSGlFKUaBVLkGgWR0ChBw6r/82rdX2UKGgGaAloD0MIZw5JLZQ6QUCUhpRSlGgVS2FoFkdAoQeKBVdX1nV9lChoBmgJaA9DCDbOpiMAgGVAlIaUUpRoFU3oA2gWR0ChB+Yt6HCXdX2UKGgGaAloD0MIJvxSP29EQUCUhpRSlGgVS3FoFkdAoR03CqIacnV9lChoBmgJaA9DCGJlNPJ5DUtAlIaUUpRoFUuZaBZHQKEdzakAPup1fZQoaAZoCWgPQwjVJHhDGpX9P5SGlFKUaBVLj2gWR0ChIRGPgeijdX2UKGgGaAloD0MI51Wd1YIlYECUhpRSlGgVTegDaBZHQKEiDkzXSSh1fZQoaAZoCWgPQwi/mC1ZFfJjQJSGlFKUaBVN6ANoFkdAoSLu5vtMPHV9lChoBmgJaA9DCICbxYsFk2FAlIaUUpRoFU3oA2gWR0ChJAMnqmj1dX2UKGgGaAloD0MI1PGYgUphZkCUhpRSlGgVTegDaBZHQKEmHBMSK3x1fZQoaAZoCWgPQwgjLgCN0n1gQJSGlFKUaBVN6ANoFkdAoSY3nwG4Z3V9lChoBmgJaA9DCJKTiVuFCmVAlIaUUpRoFU3oA2gWR0ChJsANwzcidX2UKGgGaAloD0MIXru04bCsM0CUhpRSlGgVS4loFkdAoSmGvpyIYXV9lChoBmgJaA9DCC8xlukXbWNAlIaUUpRoFU3oA2gWR0ChKdX3QD3edX2UKGgGaAloD0MI7KF9rGAQZ0CUhpRSlGgVTegDaBZHQKEr8QJXyRV1fZQoaAZoCWgPQwjay7bT1vAzQJSGlFKUaBVLlGgWR0ChL/Q4CIUKdX2UKGgGaAloD0MIUYcVbnltYUCUhpRSlGgVTegDaBZHQKEzJhUBGQV1fZQoaAZoCWgPQwg9nStKif1jQJSGlFKUaBVN6ANoFkdAoTPTvb48EHV9lChoBmgJaA9DCGLX9nbLD2ZAlIaUUpRoFU3oA2gWR0ChNO4HgP3BdX2UKGgGaAloD0MIhIQoX9DtY0CUhpRSlGgVTegDaBZHQKE1DxvvSc91fZQoaAZoCWgPQwjlfLH3YrxmQJSGlFKUaBVN6ANoFkdAoTWQ++ueSXV9lChoBmgJaA9DCGxDxTj/kGNAlIaUUpRoFU3oA2gWR0ChNeb9ZRsNdWUu"
|
87 |
+
},
|
88 |
+
"ep_success_buffer": {
|
89 |
+
":type:": "<class 'collections.deque'>",
|
90 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
91 |
+
},
|
92 |
+
"_n_updates": 368,
|
93 |
+
"n_steps": 1024,
|
94 |
+
"gamma": 0.997,
|
95 |
+
"gae_lambda": 0.98,
|
96 |
+
"ent_coef": 0.01,
|
97 |
+
"vf_coef": 0.5,
|
98 |
+
"max_grad_norm": 0.5,
|
99 |
+
"batch_size": 32,
|
100 |
+
"n_epochs": 4,
|
101 |
+
"clip_range": {
|
102 |
+
":type:": "<class 'function'>",
|
103 |
+
":serialized:": "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"
|
104 |
+
},
|
105 |
+
"clip_range_vf": null,
|
106 |
+
"normalize_advantage": true,
|
107 |
+
"target_kl": null
|
108 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b571b87b7e3870d3b920e8e4ffcfafffc8f25788fcb5ec1e84d88cef42dd869
|
3 |
+
size 944541
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:057a5d51d5cbcd1ca242d4b8d4a2e6d1a6b68a5e65042687aeee2305a7cdfa97
|
3 |
+
size 473025
|
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:f30bf8103dc8a143a91d0cb49cf79859fa1ceb91b73f95ec54b00d2fb4bf1fc6
|
3 |
+
size 243444
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 203.88642673670128, "std_reward": 88.12835041879998, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T19:02:12.656882"}
|