Python DeterministicSoftPolicy Examples

Programming Language: Python

Namespace/Package Name: behavior_regularized_offline_rl.brac.policies

Method/Function: DeterministicSoftPolicy

Examples at hotexamples.com: 2

Python DeterministicSoftPolicy - 2 examples found. These are the top rated real world Python examples of behavior_regularized_offline_rl.brac.policies.DeterministicSoftPolicy extracted from open source projects. You can rate examples to help us improve the quality of examples.

Example #1

Show file

File: brac_dual_agent.py Project: yeshwanthv5/google-research

 def _build_test_policies(self):
     policy = policies.DeterministicSoftPolicy(
         a_network=self._agent_module.p_net)
     self._test_policies['main'] = policy
     policy = policies.MaxQSoftPolicy(
         a_network=self._agent_module.p_net,
         q_network=self._agent_module.q_nets[0][0],
     )
     self._test_policies['max_q'] = policy

Example #2

Show file

File: bc_agent.py Project: shih29242890/AI_google-research

 def _build_test_policies(self):
   policy = policies.DeterministicSoftPolicy(
       a_network=self._agent_module.p_net)
   self._test_policies['main'] = policy