Add Hopper-v4_PPO
#3
by
gsc579
- opened
- Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/config.yaml +73 -0
- Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/logs/log.txt +167 -0
- Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/tb_logs/interact/events.out.tfevents.1685251458.gscaimax.2603105.0 +3 -0
- Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/tb_logs/model/events.out.tfevents.1685251458.gscaimax.2603105.1 +3 -0
- Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/config.yaml +73 -0
- Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/logs/log.txt +0 -0
- Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/models/500 +3 -0
- Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/models/best +0 -0
- Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/tb_logs/interact/events.out.tfevents.1685109393.gscaimax.2069774.0 +3 -0
- Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/tb_logs/model/events.out.tfevents.1685109393.gscaimax.2069774.1 +3 -0
Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/config.yaml
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
general_cfg:
|
| 2 |
+
algo_name: PPO
|
| 3 |
+
collect_traj: false
|
| 4 |
+
device: cuda
|
| 5 |
+
env_name: gym
|
| 6 |
+
load_checkpoint: true
|
| 7 |
+
load_model_step: best
|
| 8 |
+
load_path: Train_single_Hopper-v4_PPO_20230526-135633
|
| 9 |
+
max_episode: 100
|
| 10 |
+
max_step: 1000
|
| 11 |
+
mode: test
|
| 12 |
+
model_save_fre: 500
|
| 13 |
+
mp_backend: single
|
| 14 |
+
n_learners: 1
|
| 15 |
+
n_workers: 2
|
| 16 |
+
online_eval: true
|
| 17 |
+
online_eval_episode: 10
|
| 18 |
+
seed: 1
|
| 19 |
+
share_buffer: true
|
| 20 |
+
algo_cfg:
|
| 21 |
+
actor_hidden_dim: 256
|
| 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: 0.0003
|
| 32 |
+
batch_size: 256
|
| 33 |
+
buffer_size: 100000
|
| 34 |
+
buffer_type: ONPOLICY_QUE
|
| 35 |
+
continuous: true
|
| 36 |
+
critic_hidden_dim: 256
|
| 37 |
+
critic_layers:
|
| 38 |
+
- activation: relu
|
| 39 |
+
layer_size:
|
| 40 |
+
- 256
|
| 41 |
+
layer_type: linear
|
| 42 |
+
- activation: relu
|
| 43 |
+
layer_size:
|
| 44 |
+
- 256
|
| 45 |
+
layer_type: linear
|
| 46 |
+
critic_loss_coef: 0.5
|
| 47 |
+
critic_lr: 0.001
|
| 48 |
+
entropy_coef: 0.01
|
| 49 |
+
eps_clip: 0.2
|
| 50 |
+
epsilon_decay: 500
|
| 51 |
+
epsilon_end: 0.01
|
| 52 |
+
epsilon_start: 0.95
|
| 53 |
+
gamma: 0.95
|
| 54 |
+
independ_actor: true
|
| 55 |
+
k_epochs: 8
|
| 56 |
+
kl_alpha: 2
|
| 57 |
+
kl_beta: 1.5
|
| 58 |
+
kl_lambda: 0.5
|
| 59 |
+
kl_target: 0.1
|
| 60 |
+
lr: 0.0001
|
| 61 |
+
min_policy: 0
|
| 62 |
+
ppo_type: clip
|
| 63 |
+
sgd_batch_size: 128
|
| 64 |
+
share_optimizer: false
|
| 65 |
+
target_update: 4
|
| 66 |
+
env_cfg:
|
| 67 |
+
id: Hopper-v4
|
| 68 |
+
ignore_params:
|
| 69 |
+
- wrapper
|
| 70 |
+
- ignore_params
|
| 71 |
+
new_step_api: true
|
| 72 |
+
render_mode: null
|
| 73 |
+
wrapper: null
|
Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/logs/log.txt
ADDED
|
@@ -0,0 +1,167 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - General Configs:
|
| 2 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ================================================================================
|
| 3 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - Name Value Type
|
| 4 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - env_name gym <class 'str'>
|
| 5 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - algo_name PPO <class 'str'>
|
| 6 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - mode test <class 'str'>
|
| 7 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - device cuda <class 'str'>
|
| 8 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - seed 1 <class 'int'>
|
| 9 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - max_episode 100 <class 'int'>
|
| 10 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - max_step 1000 <class 'int'>
|
| 11 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
|
| 12 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - mp_backend single <class 'str'>
|
| 13 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - n_workers 2 <class 'int'>
|
| 14 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - n_learners 1 <class 'int'>
|
| 15 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
|
| 16 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
|
| 17 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
|
| 18 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - model_save_fre 500 <class 'int'>
|
| 19 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
|
| 20 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - load_path Train_single_Hopper-v4_PPO_20230526-135633 <class 'str'>
|
| 21 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - load_model_step best <class 'str'>
|
| 22 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ================================================================================
|
| 23 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - Algo Configs:
|
| 24 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ================================================================================
|
| 25 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - Name Value Type
|
| 26 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
|
| 27 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
|
| 28 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ppo_type clip <class 'str'>
|
| 29 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - eps_clip 0.2 <class 'float'>
|
| 30 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - kl_target 0.1 <class 'float'>
|
| 31 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - kl_lambda 0.5 <class 'float'>
|
| 32 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - kl_beta 1.5 <class 'float'>
|
| 33 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - kl_alpha 2 <class 'int'>
|
| 34 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - continuous 1 <class 'bool'>
|
| 35 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - gamma 0.95 <class 'float'>
|
| 36 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - k_epochs 8 <class 'int'>
|
| 37 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
|
| 38 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - actor_lr 0.0003 <class 'float'>
|
| 39 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - critic_lr 0.001 <class 'float'>
|
| 40 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - critic_loss_coef 0.5 <class 'float'>
|
| 41 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - entropy_coef 0.01 <class 'float'>
|
| 42 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - batch_size 256 <class 'int'>
|
| 43 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - sgd_batch_size 128 <class 'int'>
|
| 44 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - actor_hidden_dim 256 <class 'int'>
|
| 45 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - critic_hidden_dim 256 <class 'int'>
|
| 46 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - min_policy 0 <class 'int'>
|
| 47 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
|
| 48 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
|
| 49 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - buffer_type ONPOLICY_QUE <class 'str'>
|
| 50 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - buffer_size 100000 <class 'int'>
|
| 51 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'>
|
| 52 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'>
|
| 53 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'>
|
| 54 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - target_update 4 <class 'int'>
|
| 55 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ================================================================================
|
| 56 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - Env Configs:
|
| 57 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ================================================================================
|
| 58 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - Name Value Type
|
| 59 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - id Hopper-v4 <class 'str'>
|
| 60 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - render_mode None <class 'str'>
|
| 61 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - wrapper None <class 'str'>
|
| 62 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
|
| 63 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - new_step_api 1 <class 'bool'>
|
| 64 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - ================================================================================
|
| 65 |
+
2023-05-28 05:24:18 - SimpleLog - INFO: - obs_space: Box(-inf, inf, (11,), float64), n_actions: Box(-1.0, 1.0, (3,), float32)
|
| 66 |
+
2023-05-28 05:24:20 - SimpleLog - INFO: - Start testing!
|
| 67 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 0, ep_reward: 287.75783116136296, ep_step: 133
|
| 68 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 1, ep_reward: 287.75783116136296, ep_step: 133
|
| 69 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 2, ep_reward: 287.75783116136296, ep_step: 133
|
| 70 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 3, ep_reward: 287.75783116136296, ep_step: 133
|
| 71 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 4, ep_reward: 287.75783116136296, ep_step: 133
|
| 72 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 5, ep_reward: 287.75783116136296, ep_step: 133
|
| 73 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 6, ep_reward: 287.75783116136296, ep_step: 133
|
| 74 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 7, ep_reward: 287.75783116136296, ep_step: 133
|
| 75 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 8, ep_reward: 287.75783116136296, ep_step: 133
|
| 76 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 9, ep_reward: 287.75783116136296, ep_step: 133
|
| 77 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 10, ep_reward: 287.75783116136296, ep_step: 133
|
| 78 |
+
2023-05-28 05:24:22 - SimpleLog - INFO: - episode: 11, ep_reward: 287.75783116136296, ep_step: 133
|
| 79 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 12, ep_reward: 287.75783116136296, ep_step: 133
|
| 80 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 13, ep_reward: 287.75783116136296, ep_step: 133
|
| 81 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 14, ep_reward: 287.75783116136296, ep_step: 133
|
| 82 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 15, ep_reward: 287.75783116136296, ep_step: 133
|
| 83 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 16, ep_reward: 287.75783116136296, ep_step: 133
|
| 84 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 17, ep_reward: 287.75783116136296, ep_step: 133
|
| 85 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 18, ep_reward: 287.75783116136296, ep_step: 133
|
| 86 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 19, ep_reward: 287.75783116136296, ep_step: 133
|
| 87 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 20, ep_reward: 287.75783116136296, ep_step: 133
|
| 88 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 21, ep_reward: 287.75783116136296, ep_step: 133
|
| 89 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 22, ep_reward: 287.75783116136296, ep_step: 133
|
| 90 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 23, ep_reward: 287.75783116136296, ep_step: 133
|
| 91 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 24, ep_reward: 287.75783116136296, ep_step: 133
|
| 92 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 25, ep_reward: 287.75783116136296, ep_step: 133
|
| 93 |
+
2023-05-28 05:24:23 - SimpleLog - INFO: - episode: 26, ep_reward: 287.75783116136296, ep_step: 133
|
| 94 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 27, ep_reward: 287.75783116136296, ep_step: 133
|
| 95 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 28, ep_reward: 287.75783116136296, ep_step: 133
|
| 96 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 29, ep_reward: 287.75783116136296, ep_step: 133
|
| 97 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 30, ep_reward: 287.75783116136296, ep_step: 133
|
| 98 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 31, ep_reward: 287.75783116136296, ep_step: 133
|
| 99 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 32, ep_reward: 287.75783116136296, ep_step: 133
|
| 100 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 33, ep_reward: 287.75783116136296, ep_step: 133
|
| 101 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 34, ep_reward: 287.75783116136296, ep_step: 133
|
| 102 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 35, ep_reward: 287.75783116136296, ep_step: 133
|
| 103 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 36, ep_reward: 287.75783116136296, ep_step: 133
|
| 104 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 37, ep_reward: 287.75783116136296, ep_step: 133
|
| 105 |
+
2023-05-28 05:24:24 - SimpleLog - INFO: - episode: 38, ep_reward: 287.75783116136296, ep_step: 133
|
| 106 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 39, ep_reward: 287.75783116136296, ep_step: 133
|
| 107 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 40, ep_reward: 287.75783116136296, ep_step: 133
|
| 108 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 41, ep_reward: 287.75783116136296, ep_step: 133
|
| 109 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 42, ep_reward: 287.75783116136296, ep_step: 133
|
| 110 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 43, ep_reward: 287.75783116136296, ep_step: 133
|
| 111 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 44, ep_reward: 287.75783116136296, ep_step: 133
|
| 112 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 45, ep_reward: 287.75783116136296, ep_step: 133
|
| 113 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 46, ep_reward: 287.75783116136296, ep_step: 133
|
| 114 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 47, ep_reward: 287.75783116136296, ep_step: 133
|
| 115 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 48, ep_reward: 287.75783116136296, ep_step: 133
|
| 116 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 49, ep_reward: 287.75783116136296, ep_step: 133
|
| 117 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 50, ep_reward: 287.75783116136296, ep_step: 133
|
| 118 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 51, ep_reward: 287.75783116136296, ep_step: 133
|
| 119 |
+
2023-05-28 05:24:25 - SimpleLog - INFO: - episode: 52, ep_reward: 287.75783116136296, ep_step: 133
|
| 120 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 53, ep_reward: 287.75783116136296, ep_step: 133
|
| 121 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 54, ep_reward: 287.75783116136296, ep_step: 133
|
| 122 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 55, ep_reward: 287.75783116136296, ep_step: 133
|
| 123 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 56, ep_reward: 287.75783116136296, ep_step: 133
|
| 124 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 57, ep_reward: 287.75783116136296, ep_step: 133
|
| 125 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 58, ep_reward: 287.75783116136296, ep_step: 133
|
| 126 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 59, ep_reward: 287.75783116136296, ep_step: 133
|
| 127 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 60, ep_reward: 287.75783116136296, ep_step: 133
|
| 128 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 61, ep_reward: 287.75783116136296, ep_step: 133
|
| 129 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 62, ep_reward: 287.75783116136296, ep_step: 133
|
| 130 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 63, ep_reward: 287.75783116136296, ep_step: 133
|
| 131 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 64, ep_reward: 287.75783116136296, ep_step: 133
|
| 132 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 65, ep_reward: 287.75783116136296, ep_step: 133
|
| 133 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 66, ep_reward: 287.75783116136296, ep_step: 133
|
| 134 |
+
2023-05-28 05:24:26 - SimpleLog - INFO: - episode: 67, ep_reward: 287.75783116136296, ep_step: 133
|
| 135 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 68, ep_reward: 287.75783116136296, ep_step: 133
|
| 136 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 69, ep_reward: 287.75783116136296, ep_step: 133
|
| 137 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 70, ep_reward: 287.75783116136296, ep_step: 133
|
| 138 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 71, ep_reward: 287.75783116136296, ep_step: 133
|
| 139 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 72, ep_reward: 287.75783116136296, ep_step: 133
|
| 140 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 73, ep_reward: 287.75783116136296, ep_step: 133
|
| 141 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 74, ep_reward: 287.75783116136296, ep_step: 133
|
| 142 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 75, ep_reward: 287.75783116136296, ep_step: 133
|
| 143 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 76, ep_reward: 287.75783116136296, ep_step: 133
|
| 144 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 77, ep_reward: 287.75783116136296, ep_step: 133
|
| 145 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 78, ep_reward: 287.75783116136296, ep_step: 133
|
| 146 |
+
2023-05-28 05:24:27 - SimpleLog - INFO: - episode: 79, ep_reward: 287.75783116136296, ep_step: 133
|
| 147 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 80, ep_reward: 287.75783116136296, ep_step: 133
|
| 148 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 81, ep_reward: 287.75783116136296, ep_step: 133
|
| 149 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 82, ep_reward: 287.75783116136296, ep_step: 133
|
| 150 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 83, ep_reward: 287.75783116136296, ep_step: 133
|
| 151 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 84, ep_reward: 287.75783116136296, ep_step: 133
|
| 152 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 85, ep_reward: 287.75783116136296, ep_step: 133
|
| 153 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 86, ep_reward: 287.75783116136296, ep_step: 133
|
| 154 |
+
2023-05-28 05:24:28 - SimpleLog - INFO: - episode: 87, ep_reward: 287.75783116136296, ep_step: 133
|
| 155 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 88, ep_reward: 287.75783116136296, ep_step: 133
|
| 156 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 89, ep_reward: 287.75783116136296, ep_step: 133
|
| 157 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 90, ep_reward: 287.75783116136296, ep_step: 133
|
| 158 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 91, ep_reward: 287.75783116136296, ep_step: 133
|
| 159 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 92, ep_reward: 287.75783116136296, ep_step: 133
|
| 160 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 93, ep_reward: 287.75783116136296, ep_step: 133
|
| 161 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 94, ep_reward: 287.75783116136296, ep_step: 133
|
| 162 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 95, ep_reward: 287.75783116136296, ep_step: 133
|
| 163 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 96, ep_reward: 287.75783116136296, ep_step: 133
|
| 164 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 97, ep_reward: 287.75783116136296, ep_step: 133
|
| 165 |
+
2023-05-28 05:24:29 - SimpleLog - INFO: - episode: 98, ep_reward: 287.75783116136296, ep_step: 133
|
| 166 |
+
2023-05-28 05:24:30 - SimpleLog - INFO: - episode: 99, ep_reward: 287.75783116136296, ep_step: 133
|
| 167 |
+
2023-05-28 05:24:30 - SimpleLog - INFO: - Finish testing! total time consumed: 11.35s
|
Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/tb_logs/interact/events.out.tfevents.1685251458.gscaimax.2603105.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7e05ed552e4355ef41ac016904402031b14107fc27bceb4bd140d70ebb9bdfb
|
| 3 |
+
size 10236
|
Hopper-v4/Test_single_Hopper-v4_PPO_20230528-052418/tb_logs/model/events.out.tfevents.1685251458.gscaimax.2603105.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a30be333cf2d0479d9c4004eae37ff7b87d195aca009688e66f9a3a2d8c364d6
|
| 3 |
+
size 40
|
Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/config.yaml
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
general_cfg:
|
| 2 |
+
algo_name: PPO
|
| 3 |
+
collect_traj: false
|
| 4 |
+
device: cuda
|
| 5 |
+
env_name: gym
|
| 6 |
+
load_checkpoint: false
|
| 7 |
+
load_model_step: best
|
| 8 |
+
load_path: Train_single_CartPole-v1_DQN_20230515-211721
|
| 9 |
+
max_episode: 2000
|
| 10 |
+
max_step: 1000
|
| 11 |
+
mode: train
|
| 12 |
+
model_save_fre: 500
|
| 13 |
+
mp_backend: single
|
| 14 |
+
n_learners: 1
|
| 15 |
+
n_workers: 2
|
| 16 |
+
online_eval: true
|
| 17 |
+
online_eval_episode: 10
|
| 18 |
+
seed: 1
|
| 19 |
+
share_buffer: true
|
| 20 |
+
algo_cfg:
|
| 21 |
+
actor_hidden_dim: 256
|
| 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: 0.0003
|
| 32 |
+
batch_size: 256
|
| 33 |
+
buffer_size: 100000
|
| 34 |
+
buffer_type: ONPOLICY_QUE
|
| 35 |
+
continuous: true
|
| 36 |
+
critic_hidden_dim: 256
|
| 37 |
+
critic_layers:
|
| 38 |
+
- activation: relu
|
| 39 |
+
layer_size:
|
| 40 |
+
- 256
|
| 41 |
+
layer_type: linear
|
| 42 |
+
- activation: relu
|
| 43 |
+
layer_size:
|
| 44 |
+
- 256
|
| 45 |
+
layer_type: linear
|
| 46 |
+
critic_loss_coef: 0.5
|
| 47 |
+
critic_lr: 0.001
|
| 48 |
+
entropy_coef: 0.01
|
| 49 |
+
eps_clip: 0.2
|
| 50 |
+
epsilon_decay: 500
|
| 51 |
+
epsilon_end: 0.01
|
| 52 |
+
epsilon_start: 0.95
|
| 53 |
+
gamma: 0.95
|
| 54 |
+
independ_actor: true
|
| 55 |
+
k_epochs: 8
|
| 56 |
+
kl_alpha: 2
|
| 57 |
+
kl_beta: 1.5
|
| 58 |
+
kl_lambda: 0.5
|
| 59 |
+
kl_target: 0.1
|
| 60 |
+
lr: 0.0001
|
| 61 |
+
min_policy: 0
|
| 62 |
+
ppo_type: clip
|
| 63 |
+
sgd_batch_size: 128
|
| 64 |
+
share_optimizer: false
|
| 65 |
+
target_update: 4
|
| 66 |
+
env_cfg:
|
| 67 |
+
id: Hopper-v4
|
| 68 |
+
ignore_params:
|
| 69 |
+
- wrapper
|
| 70 |
+
- ignore_params
|
| 71 |
+
new_step_api: true
|
| 72 |
+
render_mode: null
|
| 73 |
+
wrapper: null
|
Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/logs/log.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/models/500
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f30fe4b81de5615f7aa072f32cb78be244894e89f342362fa71f5e861c1e324
|
| 3 |
+
size 559234
|
Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/models/best
ADDED
|
Binary file (559 kB). View file
|
|
|
Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/tb_logs/interact/events.out.tfevents.1685109393.gscaimax.2069774.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d336f8ce6688cc086c520124c6229dfb70d2c7cb4809fbb4d34c1980b0bce0f7
|
| 3 |
+
size 211780
|
Hopper-v4/Train_single_Hopper-v4_PPO_20230526-135633/tb_logs/model/events.out.tfevents.1685109393.gscaimax.2069774.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92162a641de15d129708d2ca49d12766fcff60b186e93d4cecb59f86b89d2176
|
| 3 |
+
size 129875
|