tanbwilson
commited on
Commit
•
0ce39b1
1
Parent(s):
3bed163
Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +36 -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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 196.23 +/- 70.55
|
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**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
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 0x7f9f42eba4d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9f42eba560>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9f42eba5f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9f42eba680>", "_build": "<function ActorCriticPolicy._build at 0x7f9f42eba710>", "forward": "<function ActorCriticPolicy.forward at 0x7f9f42eba7a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9f42eba830>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9f42eba8c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9f42eba950>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9f42eba9e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9f42ebaa70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f9f42f00ba0>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1655249899.5166113, "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:": "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": 124, "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:b7a29552a1d56ac9a804535ef1610fecbffebbc66b43eb71bf899091a59d9988
|
3 |
+
size 144148
|
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 0x7f9f42eba4d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9f42eba560>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9f42eba5f0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9f42eba680>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9f42eba710>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9f42eba7a0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9f42eba830>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9f42eba8c0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9f42eba950>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9f42eba9e0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9f42ebaa70>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f9f42f00ba0>"
|
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": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1655249899.5166113,
|
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:": "gASVexAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIJcy0/Ss8WECUhpRSlIwBbJRN6AOMAXSUR0B7H4B7u2JBdX2UKGgGaAloD0MIg6EOK9z6V0CUhpRSlGgVTegDaBZHQHskbpaA4GV1fZQoaAZoCWgPQwiPxMvTuVNgQJSGlFKUaBVN6ANoFkdAeyVipvP1MHV9lChoBmgJaA9DCGJM+nspV2BAlIaUUpRoFU3oA2gWR0B7Q+hK15SndX2UKGgGaAloD0MInu488ZwJYECUhpRSlGgVTegDaBZHQHt0Tu8brC51fZQoaAZoCWgPQwi5GW7A53heQJSGlFKUaBVN6ANoFkdAe5p5O8Cgb3V9lChoBmgJaA9DCHCWkuUkPWBAlIaUUpRoFU3oA2gWR0B7rvCqIacadX2UKGgGaAloD0MI9KYiFUabYECUhpRSlGgVTegDaBZHQHuxhkqc3ER1fZQoaAZoCWgPQwjj3vyGiZ9jQJSGlFKUaBVN6ANoFkdAe8zfozN2T3V9lChoBmgJaA9DCE1oklhS8VtAlIaUUpRoFU3oA2gWR0B70PzJ6po9dX2UKGgGaAloD0MI7PtwkBDiW0CUhpRSlGgVTegDaBZHQHw5pBLPD511fZQoaAZoCWgPQwiD91W50C5gQJSGlFKUaBVN6ANoFkdAfEA/LDAJs3V9lChoBmgJaA9DCFTgZBs4KGFAlIaUUpRoFU3oA2gWR0B8VwADJU5udX2UKGgGaAloD0MIa32R0JbBXUCUhpRSlGgVTegDaBZHQHxZTtLL6k91fZQoaAZoCWgPQwiqDU5EPzpkQJSGlFKUaBVN6ANoFkdAfGxHxBmf5HV9lChoBmgJaA9DCLd++s8aRGRAlIaUUpRoFU3oA2gWR0B8fDodMj/udX2UKGgGaAloD0MI9s/TgEFHZUCUhpRSlGgVTegDaBZHQHx8wzch1T11fZQoaAZoCWgPQwh6xVOPNOpfQJSGlFKUaBVN6ANoFkdAfIJKEnLJS3V9lChoBmgJaA9DCJBN8iN+sl1AlIaUUpRoFU3oA2gWR0B8gz2WY4Q0dX2UKGgGaAloD0MIJ2w/GWPhYUCUhpRSlGgVTegDaBZHQHyhXEVFhG91fZQoaAZoCWgPQwiwAny3eU8+QJSGlFKUaBVL52gWR0B8pmxcE/0NdX2UKGgGaAloD0MIT+eKUkKxV0CUhpRSlGgVTegDaBZHQHzNuwX668R1fZQoaAZoCWgPQwjc1avI6A9jQJSGlFKUaBVN6ANoFkdAfPOxA0Kqn3V9lChoBmgJaA9DCMefqGxY/llAlIaUUpRoFU3oA2gWR0B9CI2CNCJGdX2UKGgGaAloD0MIxRuZR/5FW0CUhpRSlGgVTegDaBZHQH0LRVhkRSR1fZQoaAZoCWgPQwiaCYZzjadhQJSGlFKUaBVN6ANoFkdAfSnBgNPP9nV9lChoBmgJaA9DCPMf0m9fQVNAlIaUUpRoFU3oA2gWR0B9LjKeTV2BdX2UKGgGaAloD0MIHH3MBwR8ZECUhpRSlGgVTegDaBZHQH2b7qhUR4B1fZQoaAZoCWgPQwiMKy6OSu9lQJSGlFKUaBVN6ANoFkdAfaMFtsN2DHV9lChoBmgJaA9DCLr5RnTPfGJAlIaUUpRoFU3oA2gWR0B9ugLqlgtwdX2UKGgGaAloD0MIgVziyIMmYUCUhpRSlGgVTegDaBZHQH28JGax5cF1fZQoaAZoCWgPQwjbNoyC4BhdQJSGlFKUaBVN6ANoFkdAfd3LS/j81nV9lChoBmgJaA9DCL1TAfe8hGFAlIaUUpRoFU3oA2gWR0B93lMlC1JEdX2UKGgGaAloD0MIJy7HKxDXTkCUhpRSlGgVTegDaBZHQH3kDYh+vyN1fZQoaAZoCWgPQwhlijkIuhdhQJSGlFKUaBVN6ANoFkdAfeUSH/Lkj3V9lChoBmgJaA9DCAWIghlTtWFAlIaUUpRoFU3oA2gWR0B+Bdm16Vt5dX2UKGgGaAloD0MIbQIMy5//YECUhpRSlGgVTegDaBZHQH4Lf6wdKdx1fZQoaAZoCWgPQwi37uapDjJbQJSGlFKUaBVN6ANoFkdAfjcuA7Ppp3V9lChoBmgJaA9DCHBgcqPIW19AlIaUUpRoFU3oA2gWR0B+Xw7IT4+KdX2UKGgGaAloD0MImdcRh2yeXECUhpRSlGgVTegDaBZHQH507Vz6rNp1fZQoaAZoCWgPQwjkLOxph/VhQJSGlFKUaBVN6ANoFkdAfnfF6Rhc7nV9lChoBmgJaA9DCP5l9+RhuGFAlIaUUpRoFU3oA2gWR0B+lpfQa72+dX2UKGgGaAloD0MIsaNxqF9ZZUCUhpRSlGgVTegDaBZHQH6bRBE8aGZ1fZQoaAZoCWgPQwg3ww34/Ew5QJSGlFKUaBVL32gWR0B+pP961LJ0dX2UKGgGaAloD0MIyJQPQVUTYkCUhpRSlGgVTegDaBZHQH8KGg3974V1fZQoaAZoCWgPQwjh05y8yFRiQJSGlFKUaBVN6ANoFkdAfxFIyCWeH3V9lChoBmgJaA9DCMkfDDz37ELAlIaUUpRoFU0uAWgWR0B/Gg+5e7cxdX2UKGgGaAloD0MIscHCSZpQY0CUhpRSlGgVTegDaBZHQH8pR15jYqZ1fZQoaAZoCWgPQwiaXIyB9UZgQJSGlFKUaBVN6ANoFkdAfyuEE1VHWnV9lChoBmgJaA9DCMMN+Pwwwl1AlIaUUpRoFU3oA2gWR0B/UcKkVN5/dX2UKGgGaAloD0MIKhkAqrjnV0CUhpRSlGgVTegDaBZHQH9SihakhzN1fZQoaAZoCWgPQwjA0CNGz1hfQJSGlFKUaBVN6ANoFkdAf1uMg2ZRbnV9lChoBmgJaA9DCIZa07xjk2BAlIaUUpRoFU3oA2gWR0B/XUzGgi/xdX2UKGgGaAloD0MIlL2lnK+NYECUhpRSlGgVTegDaBZHQH+CMCcPOIJ1fZQoaAZoCWgPQwgMkGgCRbFbQJSGlFKUaBVN6ANoFkdAf4dfGuLaVXV9lChoBmgJaA9DCBNFSN3OO2BAlIaUUpRoFU3oA2gWR0B/r9uIhyKfdX2UKGgGaAloD0MI10tTBDiZQUCUhpRSlGgVTTYBaBZHQH/XeU6gdwN1fZQoaAZoCWgPQwhLsDic+eRgQJSGlFKUaBVN6ANoFkdAf+jnYQJ5V3V9lChoBmgJaA9DCHTqymf5k2BAlIaUUpRoFU3oA2gWR0CAAsxDb8FZdX2UKGgGaAloD0MIk3GMZI9sX0CUhpRSlGgVTegDaBZHQIAE+bPQfIV1fZQoaAZoCWgPQwiXHk31ZMpdQJSGlFKUaBVN6ANoFkdAgAltRNyo43V9lChoBmgJaA9DCFqD91W5VFpAlIaUUpRoFU3oA2gWR0CAOcSUTtb+dX2UKGgGaAloD0MIQMIwYEnbYECUhpRSlGgVTegDaBZHQIA88Eq2Brh1fZQoaAZoCWgPQwjT2cngqN1gQJSGlFKUaBVN6ANoFkdAgEDVK5Cng3V9lChoBmgJaA9DCAZKCiwAp2BAlIaUUpRoFU3oA2gWR0CARyPI4lyBdX2UKGgGaAloD0MIF5tWCoG2UkCUhpRSlGgVTegDaBZHQIBIIQ176YV1fZQoaAZoCWgPQwhbXrneNsBhQJSGlFKUaBVN6ANoFkdAgFdK6vq1PXV9lChoBmgJaA9DCDc3picsN2NAlIaUUpRoFU3oA2gWR0CAV4ejEehgdX2UKGgGaAloD0MIPdNLjOW5YkCUhpRSlGgVTegDaBZHQIBaDf779AJ1fZQoaAZoCWgPQwhQcLGihmtgQJSGlFKUaBVN6ANoFkdAgFp9zGPxQXV9lChoBmgJaA9DCNifxOdOAF1AlIaUUpRoFU3oA2gWR0CAbQaF23a0dX2UKGgGaAloD0MItcagE8IdZECUhpRSlGgVTegDaBZHQICC9Hc1wYN1fZQoaAZoCWgPQwhyUMJM209cQJSGlFKUaBVN6ANoFkdAgJl5jYqXnnV9lChoBmgJaA9DCEWhZd2/eGJAlIaUUpRoFU3oA2gWR0CAokO6unuRdX2UKGgGaAloD0MIbD8Z40PLYUCUhpRSlGgVTegDaBZHQICw47gbZOB1fZQoaAZoCWgPQwid1QJ7zAFiQJSGlFKUaBVN6ANoFkdAgLMaXBxgiXV9lChoBmgJaA9DCHTQJRx67FpAlIaUUpRoFU3oA2gWR0CAt5XumaYvdX2UKGgGaAloD0MIZYuk3ehdYkCUhpRSlGgVTegDaBZHQIDDVd1MdtF1fZQoaAZoCWgPQwiI2cu206Y6wJSGlFKUaBVNQQFoFkdAgOnZH/cWTHV9lChoBmgJaA9DCAK6L2c2s2BAlIaUUpRoFU3oA2gWR0CA6gi5d4VzdX2UKGgGaAloD0MI2bPnMjXzXUCUhpRSlGgVTegDaBZHQIDtg+dK/VR1fZQoaAZoCWgPQwiL4eoAiEpZQJSGlFKUaBVN6ANoFkdAgPN3RPXTVnV9lChoBmgJaA9DCKlKW1zjGzbAlIaUUpRoFUvoaBZHQIDzk89wFTx1fZQoaAZoCWgPQwiAKJgxhSdkQJSGlFKUaBVN6ANoFkdAgPRUsnRb8nV9lChoBmgJaA9DCN1c/G1Po19AlIaUUpRoFU3oA2gWR0CBAYi0OVgQdX2UKGgGaAloD0MIPBIvT2dbYECUhpRSlGgVTegDaBZHQIEBv9vS+g11fZQoaAZoCWgPQwigMv59xoNiQJSGlFKUaBVN6ANoFkdAgQPWtlqagHV9lChoBmgJaA9DCI0MchfhiGBAlIaUUpRoFU3oA2gWR0CBBDN1QqI8dX2UKGgGaAloD0MIjGoRUUxqQECUhpRSlGgVS+1oFkdAgQvOEVWS2nV9lChoBmgJaA9DCCo6kst/GBrAlIaUUpRoFU0xAWgWR0CBEz0CA+Y/dX2UKGgGaAloD0MI2h694T61WUCUhpRSlGgVTegDaBZHQIETXgLqlgt1fZQoaAZoCWgPQwhORSqMLeQlQJSGlFKUaBVL92gWR0CBHVjQRf4RdX2UKGgGaAloD0MI34sv2mPzYkCUhpRSlGgVTegDaBZHQIEjksxwhnt1fZQoaAZoCWgPQwi5GAPrOB4kQJSGlFKUaBVL/2gWR0CBMIFRpDeCdX2UKGgGaAloD0MIGt1B7EyeYkCUhpRSlGgVTegDaBZHQIE88I1LrX11fZQoaAZoCWgPQwjD2EKQAwhiQJSGlFKUaBVN6ANoFkdAgUmhAv+OwXV9lChoBmgJaA9DCDGVfsJZyGRAlIaUUpRoFU3oA2gWR0CBT/ksjFAFdX2UKGgGaAloD0MImWGjrN/VYUCUhpRSlGgVTegDaBZHQIFczEm6XjV1fZQoaAZoCWgPQwh7MCk+Pt1eQJSGlFKUaBVN6ANoFkdAgV/RWT5ft3V9lChoBmgJaA9DCJ3VAnvMJmJAlIaUUpRoFU3oA2gWR0CBX/YxL0z1dWUu"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 124,
|
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:f66522f917bd81661c49e99d527af6851068b63b377ad7ede1f8d4a56a51ac56
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12c2d085125fc61c18e4f5760954515526ef576e4a68eee4dd7af0ea0f45818f
|
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 sha256:60b28c8e9a447e6561885cba02bad4a934eaa0568f90618df85854995c82c41e
|
3 |
+
size 274398
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 196.226753698957, "std_reward": 70.55185530810631, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-14T23:53:37.811673"}
|