Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo_lunar_v_500000.zip +3 -0
- ppo_lunar_v_500000/_stable_baselines3_version +1 -0
- ppo_lunar_v_500000/data +99 -0
- ppo_lunar_v_500000/policy.optimizer.pth +3 -0
- ppo_lunar_v_500000/policy.pth +3 -0
- ppo_lunar_v_500000/pytorch_variables.pth +3 -0
- ppo_lunar_v_500000/system_info.txt +9 -0
- replay.mp4 +0 -0
- results.json +1 -0
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: 242.85 +/- 51.22
|
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 0x7bdbec58e3b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7bdbec58e440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7bdbec58e4d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7bdbec58e560>", "_build": "<function ActorCriticPolicy._build at 0x7bdbec58e5f0>", "forward": "<function ActorCriticPolicy.forward at 0x7bdbec58e680>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7bdbec58e710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7bdbec58e7a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7bdbec58e830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7bdbec58e8c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7bdbec58e950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7bdbec58e9e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bdbec583740>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690281707996677161, "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": -0.04857599999999995, "_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": 480, "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": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo_lunar_v_500000.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4e9cbaea3a9fc19b06ce372e66de31e64cfdf03c91b3463b59843093732a9f2
|
3 |
+
size 146657
|
ppo_lunar_v_500000/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo_lunar_v_500000/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 0x7bdbec58e3b0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7bdbec58e440>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7bdbec58e4d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7bdbec58e560>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7bdbec58e5f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7bdbec58e680>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7bdbec58e710>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7bdbec58e7a0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7bdbec58e830>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7bdbec58e8c0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7bdbec58e950>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7bdbec58e9e0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7bdbec583740>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 524288,
|
25 |
+
"_total_timesteps": 500000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1690281707996677161,
|
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": -0.04857599999999995,
|
45 |
+
"_stats_window_size": 100,
|
46 |
+
"ep_info_buffer": {
|
47 |
+
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "gAWV/gsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG6lJ4KQaJiMAWyUTQcBjAF0lEdAsbouM98qnXV9lChoBkdAazc6fapPymgHTZQDaAhHQLG6SaIN3GJ1fZQoaAZHQHDuu6Ae7tloB0vkaAhHQLG6aU4JeE91fZQoaAZHQHEPP1g6U7loB0vTaAhHQLG65BWxQi11fZQoaAZHQGDh+kpI+W5oB03oA2gIR0CxuyIzFdcCdX2UKGgGR0BuS2JP69CeaAdL1WgIR0CxuzBTn7pFdX2UKGgGR0BekrCBPKuCaAdN6ANoCEdAsbuXX7Lt/nV9lChoBkdAYRuNXHR1HWgHTegDaAhHQLHRiXKKYRd1fZQoaAZHQHP6UZm7J4loB0vQaAhHQLHR/VyWAwx1fZQoaAZHQHBWvgJkXk5oB0v2aAhHQLHSiAsTWXl1fZQoaAZHQHIM/fKp1ihoB0vSaAhHQLHSm4WDYiB1fZQoaAZHQGJy2d3B55ZoB03oA2gIR0Cx0rS83++/dX2UKGgGR0BvL/hZQpF1aAdNMAFoCEdAsdLtEa2nbnV9lChoBkdAcGJ+UhV2imgHS91oCEdAsdL8ifQKKHV9lChoBkdAbh28QI2OyWgHS+xoCEdAsdOHEqDsdHV9lChoBkdAcCJECvHLimgHS9xoCEdAsdPR+pfhM3V9lChoBkdAcG7zTF2mpGgHS8hoCEdAsdQY2CNCJHV9lChoBkdAYzsj6eoUBWgHTegDaAhHQLHUbcHGCI11fZQoaAZHQHEGcrI5o5BoB0vCaAhHQLHUvFRHf/F1fZQoaAZHQHD2s81XNkhoB0vRaAhHQLHUy9XcQAd1fZQoaAZHQHGfePeYUnJoB00bAmgIR0Cx1SJKnNxEdX2UKGgGR0BxoCG1x82KaAdL+mgIR0Cx1ShODaoNdX2UKGgGR0BumBR/EwWWaAdL1GgIR0Cx1TaK508vdX2UKGgGR0BulCHTI/7jaAdN6QJoCEdAsdVZ5X2du3V9lChoBkdAYXyAZKnNxGgHTegDaAhHQLHWAqSHM2Z1fZQoaAZHQHC0If8uSOloB0vQaAhHQLHWOKSgXdl1fZQoaAZHQHDcsS5AhStoB0v1aAhHQLHWVYwqRU51fZQoaAZHQHCdIywfQrtoB0vEaAhHQLHWZEYfnwJ1fZQoaAZHQGQZGPxQSBdoB03oA2gIR0Cx1ofMbFS9dX2UKGgGR0Bin3IU8FINaAdN6ANoCEdAsdbC2x6fJ3V9lChoBkdAccFdGiHqNmgHS9toCEdAsdbgVIqb0HV9lChoBkdAcnOtlqagEmgHS+xoCEdAsdb2EqUeMnV9lChoBkdAcDwJz1bqyGgHS8xoCEdAsdcGk9ECvHV9lChoBkdAcHU0NSZSemgHS8toCEdAsdcPAaef7XV9lChoBkdAb7s+A3DNyGgHS81oCEdAsdcsKYzBRHV9lChoBkdAcGLXpW3jMmgHS8NoCEdAsdeapQ1rI3V9lChoBkdAbnbTGYKIBWgHS+FoCEdAsdghDiOvMnV9lChoBkdAcOqSzw+dLGgHS9poCEdAsdhEiW3Sa3V9lChoBkdAcLcDp1RtQGgHS/doCEdAsdhiwt8NQXV9lChoBkdAcyPOG0u14WgHTRUBaAhHQLHYe2U0Nz91fZQoaAZHQHBsxzJZGKBoB0vZaAhHQLHYnpmEoOR1fZQoaAZHQF7f495hScdoB03oA2gIR0Cx2KxreqJedX2UKGgGR0Bt6wbIcR16aAdL1WgIR0Cx2L7/wRXfdX2UKGgGR0BxfaKpDNQkaAdLw2gIR0Cx2MUZrHlwdX2UKGgGR0BxmXz7MxGlaAdL5mgIR0Cx2M/KdQO4dX2UKGgGR0Bw49qVQhwEaAdL6WgIR0Cx2Pl0o0AMdX2UKGgGR0BwSHxgAp8XaAdL0GgIR0Cx2YVb/wRXdX2UKGgGR0BxDPjJdSl4aAdLymgIR0Cx2msU21lYdX2UKGgGR0BhlMY8+zMSaAdN6ANoCEdAsdp8is4kvHV9lChoBkdAcsP4cWCVbGgHS9poCEdAsdrTx5LRKHV9lChoBkdAcdlJN0vGqGgHS9ZoCEdAsdsl+pfhM3V9lChoBkdAa0NsLv1DjWgHTRcBaAhHQLHbSGtp22Z1fZQoaAZHQG+FAmzByjpoB0vVaAhHQLHbfSFoL5R1fZQoaAZHQGxUuARTS9doB00AAWgIR0Cx24ihBZ6ldX2UKGgGR0BuKpnBciW3aAdL9mgIR0Cx2/xD1GsndX2UKGgGR0BxmNFCswL3aAdLxmgIR0Cx2/+4b0e2dX2UKGgGR0BzsgLv1DjSaAdLwGgIR0Cx3LODFqBVdX2UKGgGR0Bx98INVinYaAdL2mgIR0Cx3Oy/GlyjdX2UKGgGR0BmG5npSrHVaAdN6ANoCEdAsdz9y2hIv3V9lChoBkdAcDb0MPSUkmgHS9JoCEdAsd1jpC8e0XV9lChoBkdAb5S+LWI42mgHS9hoCEdAsd2MFzMibHV9lChoBkdAZrU15Sm65GgHTegDaAhHQLHdm/+85CF1fZQoaAZHQHJb9+G47RxoB00QAWgIR0Cx3cU3GXHBdX2UKGgGR0BwpxwVCXyBaAdL6mgIR0Cx3d9uDSPVdX2UKGgGR0BxvT7XQMQVaAdLx2gIR0Cx3fqciGFjdX2UKGgGR0BxLLC0ngHeaAdL52gIR0Cx3kE5IYm+dX2UKGgGR0BwuUbHZK4AaAdNFgJoCEdAsd6TBMzuW3V9lChoBkdAcHXC+lCTlmgHS8hoCEdAsd6nIlt0m3V9lChoBkdAcJa9du5z52gHS8doCEdAsd7VbjcVQHV9lChoBkdAM5HLmp2lmGgHS41oCEdAsd7Z1loUSXV9lChoBkdAchtVzZHuqmgHS8NoCEdAsd7a+QEIPnV9lChoBkdAZhBFhG6PKmgHTegDaAhHQLHe/RQ79yd1fZQoaAZHQHDnJ4wAU+NoB0vBaAhHQLHfVYO2AoZ1fZQoaAZHQHKW4mCyyD9oB0v4aAhHQLHfour6tT11fZQoaAZHQHHGL0aqCH1oB0vdaAhHQLHfvkLQXyl1fZQoaAZHQHOVYbfgrH5oB0vxaAhHQLHgBVWjoIR1fZQoaAZHQHC+CO3lS0loB0vWaAhHQLHgKmJm/WV1fZQoaAZHQGNtMwtapxZoB03oA2gIR0Cx4IffoA4odX2UKGgGR0Bw+XXQMQVcaAdL7WgIR0Cx4Mrzf779dX2UKGgGR0Bxe1aPjn3daAdLz2gIR0Cx4N+vMbFTdX2UKGgGR0BvbQQQL/jsaAdNAQFoCEdAseE0h3aBZ3V9lChoBkdAdB8sYEW69WgHS9BoCEdAseFJV1fVqnV9lChoBkdAb2SS26TW5GgHS9FoCEdAseGf8TBZZHV9lChoBkdAb7g5eZ5Rj2gHS+toCEdAseH/qMWGh3V9lChoBkdAcEXF4s3AEmgHS8loCEdAseIh9d/rjnV9lChoBkdAcI9y1/lQuWgHS99oCEdAseLHNGEwnHV9lChoBkdAXj2p84Pwu2gHTegDaAhHQLHi8+sHSnd1fZQoaAZHQGBMDnvDxb1oB03oA2gIR0Cx4xL0WdmQdX2UKGgGR0Bv9HQ4S6DoaAdL5GgIR0Cx4x2iQDFIdX2UKGgGR0BwNSgbp/wzaAdL4WgIR0Cx4ypFG5MDdX2UKGgGR0Bw02+FlCkXaAdLyGgIR0Cx41O2VmjCdX2UKGgGR0Bzg/QTmGM5aAdL0WgIR0Cx41Ut/WlNdX2UKGgGR0BxTizByjpLaAdLx2gIR0Cx4/0/8l5XdX2UKGgGR0Bzn0My8BdVaAdL1GgIR0Cx5T7yQPqcdX2UKGgGR0Bikljurp7kaAdN6ANoCEdAseVFdSl3yXV9lChoBkdAcR4hUBGQS2gHS+toCEdAseVQpd8iOnV9lChoBkdAcFr6dUbT+mgHS9ZoCEdAseWIxagVXXV9lChoBkdAbukB/7SApmgHS9loCEdAseWZzkp7TnV9lChoBkdAbdIKmbb1y2gHTWABaAhHQLHl5T/Q0Gh1fZQoaAZHQHAC9YB/7SBoB00tAWgIR0Cx5gG7OE/TdWUu"
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 480,
|
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": 2048,
|
81 |
+
"gamma": 0.99,
|
82 |
+
"gae_lambda": 0.95,
|
83 |
+
"ent_coef": 0.0,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
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:": "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"
|
98 |
+
}
|
99 |
+
}
|
ppo_lunar_v_500000/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94b71efd7af7d899bea34fca3810151cb0044457a0b573f71598c03822b1c530
|
3 |
+
size 87929
|
ppo_lunar_v_500000/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:951fe0d858b6686678d0b8de38180500f29643d3ee63c83541e1f0c320bb5060
|
3 |
+
size 43329
|
ppo_lunar_v_500000/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_lunar_v_500000/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
|
2 |
+
- Python: 3.10.6
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (179 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 242.84531950000002, "std_reward": 51.22457533898217, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-25T11:26:32.287746"}
|