Diversifying Policies With Non-Markov Dispersion to Expand the Solution Space
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2024.3455257
Abstract: Policy diversity, encompassing the variety of policies an agent can adopt, enhances reinforcement learning (RL) success by fostering more robust, adaptable, and innovative problem-solving in the environment. The environment in which standard RL operates is… read more here.
Keywords: expand solution; solution; policy; dispersion ... See more keywords