Test_CartPole-v1_A2C
Browse files- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/config.yaml +56 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/logs/log.txt +171 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/10 +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/20 +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/30 +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/40 +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/50 +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/60 +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/70 +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/best +0 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/tb_logs/interact/events.out.tfevents.1687591829.ML3090.1079348.0 +3 -0
- ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/tb_logs/policy/events.out.tfevents.1687591829.ML3090.1079348.1 +3 -0
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/config.yaml
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
general_cfg:
|
| 2 |
+
algo_name: A2C
|
| 3 |
+
collect_traj: false
|
| 4 |
+
device: cpu
|
| 5 |
+
env_name: gym
|
| 6 |
+
interact_summary_fre: 1
|
| 7 |
+
load_checkpoint: true
|
| 8 |
+
load_model_step: best
|
| 9 |
+
load_path: Train_CartPole-v1_A2C_20230623-223515
|
| 10 |
+
max_episode: 100
|
| 11 |
+
max_step: 200
|
| 12 |
+
mode: test
|
| 13 |
+
model_save_fre: 10
|
| 14 |
+
model_summary_fre: 1
|
| 15 |
+
mp_backend: single
|
| 16 |
+
n_learners: 1
|
| 17 |
+
n_workers: 2
|
| 18 |
+
online_eval: true
|
| 19 |
+
online_eval_episode: 10
|
| 20 |
+
seed: 1
|
| 21 |
+
share_buffer: true
|
| 22 |
+
algo_cfg:
|
| 23 |
+
action_type: discrete
|
| 24 |
+
actor_hidden_dim: 256
|
| 25 |
+
actor_layers:
|
| 26 |
+
- activation: relu
|
| 27 |
+
layer_size:
|
| 28 |
+
- 128
|
| 29 |
+
layer_type: linear
|
| 30 |
+
actor_lr: 0.001
|
| 31 |
+
batch_size: 256
|
| 32 |
+
buffer_type: ONPOLICY_QUE
|
| 33 |
+
critic_hidden_dim: 256
|
| 34 |
+
critic_layers:
|
| 35 |
+
- activation: relu
|
| 36 |
+
layer_size:
|
| 37 |
+
- 128
|
| 38 |
+
layer_type: linear
|
| 39 |
+
critic_loss_coef: 0.5
|
| 40 |
+
critic_lr: 0.01
|
| 41 |
+
entropy_coef: 0.01
|
| 42 |
+
gamma: 0.98
|
| 43 |
+
independ_actor: true
|
| 44 |
+
k_epochs: 4
|
| 45 |
+
lr: 0.0001
|
| 46 |
+
min_policy: 0
|
| 47 |
+
n_steps_per_learn: 1
|
| 48 |
+
sgd_batch_size: 128
|
| 49 |
+
share_optimizer: false
|
| 50 |
+
env_cfg:
|
| 51 |
+
id: CartPole-v1
|
| 52 |
+
ignore_params:
|
| 53 |
+
- wrapper
|
| 54 |
+
- ignore_params
|
| 55 |
+
render_mode: null
|
| 56 |
+
wrapper: null
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/logs/log.txt
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - General Configs:
|
| 2 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
|
| 3 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - Name Value Type
|
| 4 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - env_name gym <class 'str'>
|
| 5 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - algo_name A2C <class 'str'>
|
| 6 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - mode test <class 'str'>
|
| 7 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - device cpu <class 'str'>
|
| 8 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - seed 1 <class 'int'>
|
| 9 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - max_episode 100 <class 'int'>
|
| 10 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - max_step 200 <class 'int'>
|
| 11 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
|
| 12 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - mp_backend single <class 'str'>
|
| 13 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - n_workers 2 <class 'int'>
|
| 14 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - n_learners 1 <class 'int'>
|
| 15 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
|
| 16 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
|
| 17 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
|
| 18 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - model_save_fre 10 <class 'int'>
|
| 19 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
|
| 20 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - load_path Train_CartPole-v1_A2C_20230623-223515 <class 'str'>
|
| 21 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - load_model_step best <class 'str'>
|
| 22 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
|
| 23 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
|
| 24 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
|
| 25 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - Algo Configs:
|
| 26 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
|
| 27 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - Name Value Type
|
| 28 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
|
| 29 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
|
| 30 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - action_type discrete <class 'str'>
|
| 31 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - gamma 0.98 <class 'float'>
|
| 32 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - k_epochs 4 <class 'int'>
|
| 33 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
|
| 34 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - actor_lr 0.001 <class 'float'>
|
| 35 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_lr 0.01 <class 'float'>
|
| 36 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_loss_coef 0.5 <class 'float'>
|
| 37 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - entropy_coef 0.01 <class 'float'>
|
| 38 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - buffer_type ONPOLICY_QUE <class 'str'>
|
| 39 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - batch_size 256 <class 'int'>
|
| 40 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - sgd_batch_size 128 <class 'int'>
|
| 41 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - actor_hidden_dim 256 <class 'int'>
|
| 42 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_hidden_dim 256 <class 'int'>
|
| 43 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - min_policy 0 <class 'int'>
|
| 44 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
|
| 45 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [128], 'activation': 'relu'}] <class 'str'>
|
| 46 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [128], 'activation': 'relu'}] <class 'str'>
|
| 47 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
|
| 48 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - Env Configs:
|
| 49 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
|
| 50 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - Name Value Type
|
| 51 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - id CartPole-v1 <class 'str'>
|
| 52 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - render_mode None <class 'str'>
|
| 53 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - wrapper None <class 'str'>
|
| 54 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
|
| 55 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
|
| 56 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - Start testing!
|
| 57 |
+
2023-06-24 15:30:29 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward 200.000 in 200 steps
|
| 58 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward 200.000 in 200 steps
|
| 59 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward 200.000 in 200 steps
|
| 60 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward 200.000 in 200 steps
|
| 61 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 200.000 in 200 steps
|
| 62 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward 200.000 in 200 steps
|
| 63 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward 200.000 in 200 steps
|
| 64 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 8 with reward 200.000 in 200 steps
|
| 65 |
+
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 9 with reward 200.000 in 200 steps
|
| 66 |
+
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward 200.000 in 200 steps
|
| 67 |
+
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward 200.000 in 200 steps
|
| 68 |
+
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward 200.000 in 200 steps
|
| 69 |
+
2023-06-24 15:30:31 - SimpleLog - INFO: - update_step: 10, online_eval_reward: 200.000
|
| 70 |
+
2023-06-24 15:30:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
| 71 |
+
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward 200.000 in 200 steps
|
| 72 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward 200.000 in 200 steps
|
| 73 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward 200.000 in 200 steps
|
| 74 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 16 with reward 200.000 in 200 steps
|
| 75 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 17 with reward 200.000 in 200 steps
|
| 76 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward 18.000 in 18 steps
|
| 77 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward 200.000 in 200 steps
|
| 78 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward 200.000 in 200 steps
|
| 79 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 21 with reward 200.000 in 200 steps
|
| 80 |
+
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 22 with reward 200.000 in 200 steps
|
| 81 |
+
2023-06-24 15:30:33 - SimpleLog - INFO: - Interactor 1 finished episode 23 with reward 200.000 in 200 steps
|
| 82 |
+
2023-06-24 15:30:33 - SimpleLog - INFO: - Interactor 0 finished episode 24 with reward 200.000 in 200 steps
|
| 83 |
+
2023-06-24 15:30:33 - SimpleLog - INFO: - Interactor 1 finished episode 25 with reward 200.000 in 200 steps
|
| 84 |
+
2023-06-24 15:30:33 - SimpleLog - INFO: - update_step: 20, online_eval_reward: 200.000
|
| 85 |
+
2023-06-24 15:30:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
| 86 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 26 with reward 200.000 in 200 steps
|
| 87 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 27 with reward 200.000 in 200 steps
|
| 88 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 200.000 in 200 steps
|
| 89 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 200.000 in 200 steps
|
| 90 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 30 with reward 200.000 in 200 steps
|
| 91 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 31 with reward 200.000 in 200 steps
|
| 92 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 32 with reward 200.000 in 200 steps
|
| 93 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 33 with reward 200.000 in 200 steps
|
| 94 |
+
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 34 with reward 200.000 in 200 steps
|
| 95 |
+
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 1 finished episode 35 with reward 200.000 in 200 steps
|
| 96 |
+
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 0 finished episode 36 with reward 200.000 in 200 steps
|
| 97 |
+
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward 200.000 in 200 steps
|
| 98 |
+
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward 200.000 in 200 steps
|
| 99 |
+
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 1 finished episode 39 with reward 200.000 in 200 steps
|
| 100 |
+
2023-06-24 15:30:35 - SimpleLog - INFO: - update_step: 30, online_eval_reward: 200.000
|
| 101 |
+
2023-06-24 15:30:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
| 102 |
+
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 0 finished episode 40 with reward 200.000 in 200 steps
|
| 103 |
+
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 41 with reward 200.000 in 200 steps
|
| 104 |
+
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 0 finished episode 42 with reward 200.000 in 200 steps
|
| 105 |
+
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 43 with reward 200.000 in 200 steps
|
| 106 |
+
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 0 finished episode 44 with reward 200.000 in 200 steps
|
| 107 |
+
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 45 with reward 200.000 in 200 steps
|
| 108 |
+
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward 200.000 in 200 steps
|
| 109 |
+
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 200.000 in 200 steps
|
| 110 |
+
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 0 finished episode 48 with reward 200.000 in 200 steps
|
| 111 |
+
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 1 finished episode 49 with reward 200.000 in 200 steps
|
| 112 |
+
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 0 finished episode 50 with reward 200.000 in 200 steps
|
| 113 |
+
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 1 finished episode 51 with reward 200.000 in 200 steps
|
| 114 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - update_step: 40, online_eval_reward: 200.000
|
| 115 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
| 116 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 52 with reward 200.000 in 200 steps
|
| 117 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 53 with reward 198.000 in 198 steps
|
| 118 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 54 with reward 200.000 in 200 steps
|
| 119 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward 200.000 in 200 steps
|
| 120 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward 200.000 in 200 steps
|
| 121 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 57 with reward 200.000 in 200 steps
|
| 122 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 58 with reward 200.000 in 200 steps
|
| 123 |
+
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 59 with reward 200.000 in 200 steps
|
| 124 |
+
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 0 finished episode 60 with reward 200.000 in 200 steps
|
| 125 |
+
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 1 finished episode 61 with reward 200.000 in 200 steps
|
| 126 |
+
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward 200.000 in 200 steps
|
| 127 |
+
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 200.000 in 200 steps
|
| 128 |
+
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward 200.000 in 200 steps
|
| 129 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - update_step: 50, online_eval_reward: 200.000
|
| 130 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
| 131 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward 200.000 in 200 steps
|
| 132 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 66 with reward 200.000 in 200 steps
|
| 133 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 1 finished episode 67 with reward 200.000 in 200 steps
|
| 134 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 68 with reward 200.000 in 200 steps
|
| 135 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 1 finished episode 69 with reward 200.000 in 200 steps
|
| 136 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 70 with reward 200.000 in 200 steps
|
| 137 |
+
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 1 finished episode 71 with reward 200.000 in 200 steps
|
| 138 |
+
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 0 finished episode 72 with reward 200.000 in 200 steps
|
| 139 |
+
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward 200.000 in 200 steps
|
| 140 |
+
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 200.000 in 200 steps
|
| 141 |
+
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 1 finished episode 75 with reward 200.000 in 200 steps
|
| 142 |
+
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 0 finished episode 76 with reward 200.000 in 200 steps
|
| 143 |
+
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 1 finished episode 77 with reward 200.000 in 200 steps
|
| 144 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - update_step: 60, online_eval_reward: 200.000
|
| 145 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
| 146 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 78 with reward 200.000 in 200 steps
|
| 147 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 1 finished episode 79 with reward 200.000 in 200 steps
|
| 148 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 80 with reward 200.000 in 200 steps
|
| 149 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 1 finished episode 81 with reward 200.000 in 200 steps
|
| 150 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 82 with reward 200.000 in 200 steps
|
| 151 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward 200.000 in 200 steps
|
| 152 |
+
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 1 finished episode 84 with reward 200.000 in 200 steps
|
| 153 |
+
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 1 finished episode 85 with reward 200.000 in 200 steps
|
| 154 |
+
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 0 finished episode 86 with reward 200.000 in 200 steps
|
| 155 |
+
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 1 finished episode 87 with reward 200.000 in 200 steps
|
| 156 |
+
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 0 finished episode 88 with reward 200.000 in 200 steps
|
| 157 |
+
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 1 finished episode 89 with reward 200.000 in 200 steps
|
| 158 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - update_step: 70, online_eval_reward: 200.000
|
| 159 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
| 160 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 90 with reward 200.000 in 200 steps
|
| 161 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 1 finished episode 91 with reward 200.000 in 200 steps
|
| 162 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward 200.000 in 200 steps
|
| 163 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 93 with reward 200.000 in 200 steps
|
| 164 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 94 with reward 200.000 in 200 steps
|
| 165 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 95 with reward 11.000 in 11 steps
|
| 166 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 1 finished episode 96 with reward 200.000 in 200 steps
|
| 167 |
+
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 97 with reward 200.000 in 200 steps
|
| 168 |
+
2023-06-24 15:30:45 - SimpleLog - INFO: - Interactor 1 finished episode 98 with reward 200.000 in 200 steps
|
| 169 |
+
2023-06-24 15:30:45 - SimpleLog - INFO: - Interactor 0 finished episode 99 with reward 200.000 in 200 steps
|
| 170 |
+
2023-06-24 15:30:45 - SimpleLog - INFO: - Interactor 1 finished episode 100 with reward 200.000 in 200 steps
|
| 171 |
+
2023-06-24 15:30:45 - SimpleLog - INFO: - Finish testing! Time cost: 15.808 s
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/10
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/20
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/30
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/40
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/50
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/60
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/70
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/models/best
ADDED
|
Binary file (9.62 kB). View file
|
|
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/tb_logs/interact/events.out.tfevents.1687591829.ML3090.1079348.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03847a953bafad01f0a1ab84c155fe8e9133c622eeef0d0d1fc043bd7e055e4b
|
| 3 |
+
size 9640
|
ClassControl/CartPole-v1/Test_CartPole-v1_A2C_20230624-153029/tb_logs/policy/events.out.tfevents.1687591829.ML3090.1079348.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91183e33ecb1eb9a5cfc44f89bf69dc4d50262b43ddbcc1ec978bf7fd5927ca9
|
| 3 |
+
size 12791
|