Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning

arXiv:2310.08331v2 Announce Type: replace-cross
Abstract: Incomplete knowledge of the environment leads an agent to make decisions under uncertainty. One of the major dilemmas in Reinforcement Learning (RL) where an autonomous agent has to balance two contrasting needs in making its decisions is: exploiting the current knowledge of the environment to maximize the cumulative reward as well as exploring actions that allow improving the knowledge of the environment, hopefully leading to higher reward values (exploration-exploitation trade-off). Concurrently, another relevant issue regards …

abstract agent arxiv autonomous balance cs.lg current decisions dilemmas environment exploitation exploration knowledge leads major making reinforcement reinforcement learning stat.ml the environment type uncertainty