google-deepmind / acme

A library of reinforcement learning components and agents

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DQN eval_epsilon overwrite with epsilon on 0.0

tseyde opened this issue · comments

commented

Hi Acme team, I think JAX DQN might set the evaluation epsilon to the exploration epsilon if deterministic evaluation is requested (eps=0.0, here). Replacing this with self._config.eval_epsilon is not None fixed it for me - does this also occur on your end?

Thanks so much for checking!