works on
controlled markov process 1information theory 1mutual information 1optimal policy 1reinforcement learning 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.AI2026

Calculating Mutual Information between a Reward Maximizer and its Environment

Alfred Harwood, Jose Faustino, Alex Altair

The paper derives an exact information-theoretic bound showing that an optimal deterministic policy in a Controlled Markov Process reveals n log m bits about the environment, quant…