johnjim0816
commited on
Commit
Β·
56029d5
1
Parent(s):
24d6ada
update DDPG Pendulum-v1
Browse filesThis view is limited to 50 files because it contains too many changes. Β
See raw diff
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs/log.txt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/models/actor_checkpoint.pt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/learning_curve.png +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/res.csv +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/logs/log.txt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/models/actor.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/models/critic_1.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/models/critic_2.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/results/learning_curve.png +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/results/res.csv +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/logs/log.txt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/models/actor.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/models/critic_1.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/models/critic_2.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/results/learning_curve.png +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/results/res.csv +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/logs/log.txt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/models/actor.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/models/critic_1.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/models/critic_2.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/results/learning_curve.png +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/results/res.csv +0 -0
- ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/config.yaml +56 -0
- ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/logs/log.txt +60 -0
- Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/models/actor_checkpoint.pt β ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/interact/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.0 +2 -2
- ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/model/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.1 +3 -0
- ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/videos/video.gif +3 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/logs/log.txt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/models/actor_checkpoint.pt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/learning_curve.png +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/res.csv +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/logs/log.txt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/models/checkpoint.pt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/results/learning_curve.png +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/results/res.csv +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/logs/log.txt +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/models/actor.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/models/critic_1.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/models/critic_2.pth +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/results/learning_curve.png +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/results/res.csv +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_BC_20230416-111154/config.yaml +0 -0
- {Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_BC_20230416-111154/logs/log.txt +0 -0
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs/log.txt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/models/actor_checkpoint.pt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/learning_curve.png
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/res.csv
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/logs/log.txt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/models/actor.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/models/critic_1.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/models/critic_2.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/results/learning_curve.png
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_20230416-113300/results/res.csv
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/logs/log.txt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/models/actor.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/models/critic_1.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/models/critic_2.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/results/learning_curve.png
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_TD3_BC_20230416-113155/results/res.csv
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/logs/log.txt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/models/actor.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/models/critic_1.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/models/critic_2.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/results/learning_curve.png
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Test_gym_mp_TD3_20230416-221428/results/res.csv
RENAMED
|
File without changes
|
ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/config.yaml
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
general_cfg:
|
| 2 |
+
algo_name: DDPG
|
| 3 |
+
collect_traj: false
|
| 4 |
+
device: cuda
|
| 5 |
+
env_name: gym
|
| 6 |
+
load_checkpoint: true
|
| 7 |
+
load_model_step: best
|
| 8 |
+
load_path: Train_ray_Pendulum-v1_DDPG_20230527-001715
|
| 9 |
+
max_episode: 10
|
| 10 |
+
max_step: 200
|
| 11 |
+
mode: test
|
| 12 |
+
model_save_fre: 2000
|
| 13 |
+
mp_backend: single
|
| 14 |
+
n_learners: 1
|
| 15 |
+
n_workers: 4
|
| 16 |
+
online_eval: true
|
| 17 |
+
online_eval_episode: 20
|
| 18 |
+
seed: 10
|
| 19 |
+
share_buffer: true
|
| 20 |
+
algo_cfg:
|
| 21 |
+
action_type: dpg
|
| 22 |
+
actor_layers:
|
| 23 |
+
- activation: relu
|
| 24 |
+
layer_size:
|
| 25 |
+
- 256
|
| 26 |
+
layer_type: linear
|
| 27 |
+
- activation: relu
|
| 28 |
+
layer_size:
|
| 29 |
+
- 256
|
| 30 |
+
layer_type: linear
|
| 31 |
+
actor_lr: 0.0001
|
| 32 |
+
batch_size: 128
|
| 33 |
+
buffer_size: 8000
|
| 34 |
+
buffer_type: REPLAY_QUE
|
| 35 |
+
critic_layers:
|
| 36 |
+
- activation: relu
|
| 37 |
+
layer_size:
|
| 38 |
+
- 256
|
| 39 |
+
layer_type: linear
|
| 40 |
+
- activation: relu
|
| 41 |
+
layer_size:
|
| 42 |
+
- 256
|
| 43 |
+
layer_type: linear
|
| 44 |
+
critic_lr: 0.001
|
| 45 |
+
gamma: 0.99
|
| 46 |
+
policy_loss_weight: 0.002
|
| 47 |
+
tau: 0.001
|
| 48 |
+
value_max: .inf
|
| 49 |
+
value_min: -.inf
|
| 50 |
+
env_cfg:
|
| 51 |
+
id: Pendulum-v1
|
| 52 |
+
ignore_params:
|
| 53 |
+
- wrapper
|
| 54 |
+
- ignore_params
|
| 55 |
+
render_mode: rgb_array
|
| 56 |
+
wrapper: null
|
ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/logs/log.txt
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - General Configs:
|
| 2 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
|
| 3 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type
|
| 4 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - env_name gym <class 'str'>
|
| 5 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - algo_name DDPG <class 'str'>
|
| 6 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - mode test <class 'str'>
|
| 7 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - device cuda <class 'str'>
|
| 8 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - seed 10 <class 'int'>
|
| 9 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - max_episode 10 <class 'int'>
|
| 10 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - max_step 200 <class 'int'>
|
| 11 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
|
| 12 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - mp_backend single <class 'str'>
|
| 13 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - n_workers 4 <class 'int'>
|
| 14 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - n_learners 1 <class 'int'>
|
| 15 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
|
| 16 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
|
| 17 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - online_eval_episode 20 <class 'int'>
|
| 18 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - model_save_fre 2000 <class 'int'>
|
| 19 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
|
| 20 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - load_path Train_ray_Pendulum-v1_DDPG_20230527-001715 <class 'str'>
|
| 21 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - load_model_step best <class 'str'>
|
| 22 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
|
| 23 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - Algo Configs:
|
| 24 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
|
| 25 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type
|
| 26 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - action_type dpg <class 'str'>
|
| 27 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'>
|
| 28 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - buffer_size 8000 <class 'int'>
|
| 29 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - batch_size 128 <class 'int'>
|
| 30 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - gamma 0.99 <class 'float'>
|
| 31 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - policy_loss_weight 0.002 <class 'float'>
|
| 32 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - critic_lr 0.001 <class 'float'>
|
| 33 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - actor_lr 0.0001 <class 'float'>
|
| 34 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - tau 0.001 <class 'float'>
|
| 35 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - value_min -inf <class 'float'>
|
| 36 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - value_max inf <class 'float'>
|
| 37 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
|
| 38 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
|
| 39 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
|
| 40 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - Env Configs:
|
| 41 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
|
| 42 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type
|
| 43 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - id Pendulum-v1 <class 'str'>
|
| 44 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - render_mode rgb_array <class 'str'>
|
| 45 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - wrapper None <class 'str'>
|
| 46 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
|
| 47 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
|
| 48 |
+
2023-05-27 12:07:39 - SimpleLog - INFO: - obs_space: Box([-1. -1. -8.], [1. 1. 8.], (3,), float32), n_actions: Box(-2.0, 2.0, (1,), float32)
|
| 49 |
+
2023-05-27 12:07:40 - SimpleLog - INFO: - Start testing!
|
| 50 |
+
2023-05-27 12:07:42 - SimpleLog - INFO: - episode: 0, ep_reward: -253.906, ep_step: 200
|
| 51 |
+
2023-05-27 12:07:46 - SimpleLog - INFO: - episode: 1, ep_reward: -253.906, ep_step: 200
|
| 52 |
+
2023-05-27 12:07:46 - SimpleLog - INFO: - episode: 2, ep_reward: -253.906, ep_step: 200
|
| 53 |
+
2023-05-27 12:07:47 - SimpleLog - INFO: - episode: 3, ep_reward: -253.906, ep_step: 200
|
| 54 |
+
2023-05-27 12:07:48 - SimpleLog - INFO: - episode: 4, ep_reward: -253.906, ep_step: 200
|
| 55 |
+
2023-05-27 12:07:48 - SimpleLog - INFO: - episode: 5, ep_reward: -253.906, ep_step: 200
|
| 56 |
+
2023-05-27 12:07:49 - SimpleLog - INFO: - episode: 6, ep_reward: -253.906, ep_step: 200
|
| 57 |
+
2023-05-27 12:07:50 - SimpleLog - INFO: - episode: 7, ep_reward: -253.906, ep_step: 200
|
| 58 |
+
2023-05-27 12:07:51 - SimpleLog - INFO: - episode: 8, ep_reward: -253.906, ep_step: 200
|
| 59 |
+
2023-05-27 12:07:52 - SimpleLog - INFO: - episode: 9, ep_reward: -253.906, ep_step: 200
|
| 60 |
+
2023-05-27 12:07:52 - SimpleLog - INFO: - Finish testing! total time consumed: 12.58s
|
Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/models/actor_checkpoint.pt β ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/interact/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.0
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64dbf4bf19be7aa1d79cd97ab84a6578e48107568cc32c3df036dc193e407562
|
| 3 |
+
size 996
|
ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/model/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e123931f1d5c5205cb1aa98cd172ba11f6bc0e4fb66cad15996d12535eb6d0b7
|
| 3 |
+
size 40
|
ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/videos/video.gif
ADDED
|
Git LFS Details
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/logs/log.txt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/models/actor_checkpoint.pt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/learning_curve.png
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/res.csv
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/logs/log.txt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/models/checkpoint.pt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/results/learning_curve.png
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_Pendulum-v1_SAC_20230305-114217/results/res.csv
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/logs/log.txt
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/models/actor.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/models/critic_1.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/models/critic_2.pth
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/results/learning_curve.png
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_20230416-110359/results/res.csv
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_BC_20230416-111154/config.yaml
RENAMED
|
File without changes
|
{Pendulum-v1 β ClassControl/Pendulum-v1}/Train_gym_TD3_BC_20230416-111154/logs/log.txt
RENAMED
|
File without changes
|