1e9c3ee592be5e11dcce932a73009488d6f85474,ch17/lib/common.py,,iterate_batches,#Any#Any#Any#,90
Before Change
done_rewards = []
done_steps = []
for n in range(REWARD_STEPS):
obs_v = ptan.agent.default_states_preprocessor(obs)
mb_obs[:, n] = obs_v.data.numpy()
if cuda:
obs_v = obs_v.cuda()
logits_v, values_v = net(obs_v)
After Change
done_rewards = []
done_steps = []
for n in range(REWARD_STEPS):
obs_v = ptan.agent.default_states_preprocessor(obs).to(device)
mb_obs[:, n] = obs_v.data.cpu().numpy()
logits_v, values_v = net(obs_v)
probs_v = F.softmax(logits_v, dim=1)
probs = probs_v.data.cpu().numpy()
In pattern: SUPERPATTERN
Frequency: 5
Non-data size: 3
Instances
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 1e9c3ee592be5e11dcce932a73009488d6f85474
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch17/lib/common.py
Class Name:
Method Name: iterate_batches
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 656933c471e64ad697be749b98cea93a758ac5cb
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch16/02_cheetah_es.py
Class Name:
Method Name: evaluate
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 1e9c3ee592be5e11dcce932a73009488d6f85474
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch17/02_imag.py
Class Name:
Method Name: iterate_batches
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 1e9c3ee592be5e11dcce932a73009488d6f85474
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch17/play.py
Class Name:
Method Name:
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 1e9c3ee592be5e11dcce932a73009488d6f85474
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch17/03_i2a.py
Class Name:
Method Name: