373ae159f7ae1cabaf87228d1ae0fb6acd1c6363,ch14/lib/model.py,AgentD4PG,__call__,#AgentD4PG#Any#Any#,162
Before Change
self.epsilon = epsilon
def __call__(self, states, agent_states):
states_v = ptan.agent.float32_preprocessor(states, cuda=self.cuda)
mu_v = self.net(states_v)
actions = mu_v.data.cpu().numpy()
actions += self.epsilon * np.random.normal(size=actions.shape)
actions = np.clip(actions, -1, 1)
After Change
self.epsilon = epsilon
def __call__(self, states, agent_states):
states_v = ptan.agent.float32_preprocessor(states).to(self.device)
mu_v = self.net(states_v)
actions = mu_v.data.cpu().numpy()
actions += self.epsilon * np.random.normal(size=actions.shape)
actions = np.clip(actions, -1, 1)
In pattern: SUPERPATTERN
Frequency: 4
Non-data size: 5
Instances
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 373ae159f7ae1cabaf87228d1ae0fb6acd1c6363
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch14/lib/model.py
Class Name: AgentD4PG
Method Name: __call__
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 373ae159f7ae1cabaf87228d1ae0fb6acd1c6363
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch14/lib/model.py
Class Name: AgentDDPG
Method Name: __call__
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: d5b0cd8e7960c247bb7c5b7c832358f8831780fb
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch15/lib/model.py
Class Name: AgentA2C
Method Name: __call__
Project Name: PacktPublishing/Deep-Reinforcement-Learning-Hands-On
Commit Name: 373ae159f7ae1cabaf87228d1ae0fb6acd1c6363
Time: 2018-04-29
Author: max.lapan@gmail.com
File Name: ch14/lib/model.py
Class Name: AgentA2C
Method Name: __call__