activity
20172020
most citedBiased Aggregation, Rollout, and Enhanced Policy Improvement for Reinforcement Learning

10 citations · 10 across the 3 of their papers we have counts for

collaborators

6 papers

math.OC2020

Multiagent Value Iteration Algorithms in Dynamic Programming and Reinforcement Learning

Dimitri Bertsekas

We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. In an ear…

cs.RO2020

Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration with Application to Autonomous Sequential Repair Problems

Sushmita Bhattacharya, Sahil Badyal, Thomas Wheeler +2

In this paper we consider infinite horizon discounted dynamic programming problems with finite state and control spaces, and partial state observations. We discuss an algorithm tha…

math.OC2020

Constrained Multiagent Rollout and Multidimensional Assignment with the Auction Algorithm

Dimitri Bertsekas

We consider an extension of the rollout algorithm that applies to constrained deterministic dynamic programming, including challenging combinatorial optimization problems. The algo…

cs.LG201910 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…

math.OC2017

Stable Optimal Control and Semicontractive Dynamic Programming

Dimitri P. Bertsekas

We consider discrete-time infinite horizon deterministic optimal control problems with nonnegative cost per stage, and a destination that is cost-free and absorbing. The classical…