10 citations · 22 across the 7 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2019★ 10 cited
Biased Aggregation, Rollout, and Enhanced Policy Improvement for Reinforcement Learning
Dimitri Bertsekas
We propose a new aggregation framework for approximate dynamic programming, which provides a connection with rollout algorithms, approximate policy iteration, and other single and…
cs.LG2019
Multiagent Rollout Algorithms and Reinforcement Learning
Dimitri Bertsekas
We consider finite and infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents…
cs.LG2018
Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations
Dimitri P. Bertsekas
In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods a…