dodox/metastable-baselines
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Note about Code-Src

Browse Source
This commit is contained in:
Dominik Moritz Roth 2022-06-25 15:37:45 +02:00
parent b9f66dd95d
commit 5f7cfd2e10
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
sb3_trl/trl_pg/trl_pg.py
View File

@ -230,6 +230,7 @@ class TRL_PG(OnPolicyAlgorithm):
# values, log_prob, entropy = self.policy.evaluate_actions(rollout_data.observations, actions) # values, log_prob, entropy = self.policy.evaluate_actions(rollout_data.observations, actions)
# src in TRL reference code: # src in TRL reference code:
# Stolen from Fabian's Code (Public Version):
# p = self.policy(rollout_data.observations) # p = self.policy(rollout_data.observations)
# proj_p = self.projection(self.policy, p, b_q = (b_old_mean, b_old_std), self._global_step) # proj_p = self.projection(self.policy, p, b_q = (b_old_mean, b_old_std), self._global_step)
# new_logpacs = self.policy.log_probability(proj_p, b_actions) # new_logpacs = self.policy.log_probability(proj_p, b_actions)