A sequential decision-making agent balances between exploring to gain new knowledge about an environment and exploiting current knowledge to maximize immediate reward. For environments studied in the traditional literature, optimal decisions gravitate over time toward exploitation as the agent accumulates sufficient knowledge and the benefits of further exploration vanish. What if, however, the environment offers an unlimited amount of useful knowledge and there is large benefit to further exploration no matter how much the agent has learned? We offer a simple, quintessential example of such a complex environment. In this environment, rewards are unbounded and an agent can always increase the rate at which rewards accumulate by exploring to learn more. Consequently, an optimal agent forever maintains a propensity to explore.
@article{arxiv.2407.12178,
title = {Exploration Unbound},
author = {Dilip Arumugam and Wanqiao Xu and Benjamin Van Roy},
journal= {arXiv preprint arXiv:2407.12178},
year = {2024}
}
Comments
Accepted to the Finding the Frame Workshop at RLC 2024