Hi there, Imagine we have Discrete(2) action space consiting of action_0 and action_1. In the global Environment we dont want to act every env_step, so asume action_0 is a “skip action”. (we know, when we do not need to learn). But for any Policy Environment will return its state for every step. …

Different step alignment for agent and environment

Lars_Simon_Zehnder July 29, 2021, 5:47pm 2

it’s a time now, but maybe this post here helps.

2 Likes