Markov flow policy -- deep MC

arXiv:2405.00877v1 Announce Type: new
Abstract: Discounted algorithms often encounter evaluation errors due to their reliance on short-term estimations, which can impede their efficacy in addressing simple, short-term tasks and impose undesired temporal discounts (\(\gamma\)). Interestingly, these algorithms are often tested without applying a discount, a phenomenon we refer as the \textit{train-test bias}. In response to these challenges, we propose the Markov Flow Policy, which utilizes a non-negative neural network flow to enable comprehensive forward-view predictions. Through integration into the TD7 …

abstract algorithms arxiv bias cs.ai cs.lg errors estimations evaluation flow markov policy reliance simple tasks temporal test train type