LAUSR

Self Punishment and Reward Backfill for Deep Q-Learning

Sign Up to like & get
recommendations!
3 Published in 2022 at "IEEE transactions on neural networks and learning systems"

DOI: 10.1109/tnnls.2021.3140042

Abstract: Reinforcement learning (RL) agents learn by encouraging behaviors, which maximizes their total reward, usually provided by the environment. In many environments, however, the reward is provided after a series of actions rather than each single… read more here.

Keywords: reward backfill; self punishment; two strategies; punishment reward ... See more keywords