Experimentally, it has been observed that humans and animals often make decisions that do not maximize their expected utility, but rather choose outcomes randomly, with probability proportional to expected utility. Probability matching, as this strategy is called, is equivalent to maximum entropy reinforcement learning (MaxEnt RL). However, MaxEnt RL does not optimize expected utility. In this paper, we formally show that MaxEnt RL does optimally solve certain classes of control problems with variability in the reward function. In particular, we show (1) that MaxEnt RL can be used to solve a certain class of POMDPs, and (2) that MaxEnt RL is equivalent to a two-player game where an adversary chooses the reward function. These results suggest a deeper connection between MaxEnt RL, robust control, and POMDPs, and provide insight for the types of problems for which we might expect MaxEnt RL to produce effective solutions. Specifically, our results suggest that domains with uncertainty in the task goal may be especially well-suited for MaxEnt RL methods.
Speakers: Benjamin Eysenbach, Sergey Levine