99abcc6e9b57f441999ce10dbc31ca1bed79c356,ch15/04_train_ppo.py,,,#,55

Before Change


                tb_tracker.track("advantage", adv_v, step_idx)
                tb_tracker.track("values", value_v, step_idx)
                tb_tracker.track("batch_rewards", vals_ref_v, step_idx)
                tb_tracker.track("loss_entropy", entropy_loss_v, step_idx)
                tb_tracker.track("loss_policy", loss_policy_v, step_idx)
                tb_tracker.track("loss_value", loss_value_v, step_idx)
                tb_tracker.track("loss_total", loss_v, step_idx)

After Change


    test_env = gym.make(ENV_ID)

    net_act = model.ModelActor(envs[0].observation_space.shape[0], envs[0].action_space.shape[0])
    net_crt = model.ModelCritic(envs[0].observation_space.shape[0])
    if args.cuda:
        net_act.cuda()
        net_crt.cuda()
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 5

Instances


Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 99abcc6e9b57f441999ce10dbc31ca1bed79c356
Time: 2018-02-10
Author: max.lapan@gmail.com
File Name: ch15/04_train_ppo.py
Class Name:
Method Name:


Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 21434a6920120a4d83a75e340474ef4c7c6ad972
Time: 2018-02-11
Author: max.lapan@gmail.com
File Name: ch15/04_train_ppo.py
Class Name:
Method Name:


Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 99abcc6e9b57f441999ce10dbc31ca1bed79c356
Time: 2018-02-10
Author: max.lapan@gmail.com
File Name: ch15/04_train_ppo.py
Class Name:
Method Name:


Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 4296a765125fff6491892a1bb70fb32ac516dae6
Time: 2018-02-10
Author: max.lapan@gmail.com
File Name: ch15/01_train_a2c.py
Class Name:
Method Name: