Empirical Policy Evaluation with Supergraphs

02/18/2020
by   Daniel Vial, et al.
0

We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning. Our algorithms explore backward from high-cost states to find high-value ones, in contrast to forward approaches that work forward from all states. While several papers have demonstrated the utility of backward exploration empirically, we conduct rigorous analyses which show that our algorithms can reduce average-case sample complexity from O(S log S) to as low as O(log S).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/04/2022

Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts

Traditional model-based reinforcement learning (RL) methods generate for...
research
05/11/2022

A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning

While reinforcement learning (RL) provides a framework for learning thro...
research
05/31/2023

Replicability in Reinforcement Learning

We initiate the mathematical study of replicability as an algorithmic pr...
research
07/05/2022

Empirical Evaluation of Project Scheduling Algorithms for Maximization of the Net Present Value

This paper presents an empirical performance analysis of three project s...
research
03/24/2021

Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation

Policy optimization methods are popular reinforcement learning algorithm...
research
07/05/2017

Combining Forward and Backward Abstract Interpretation of Horn Clauses

Alternation of forward and backward analyses is a standard technique in ...
research
11/10/2017

Optimised Maintenance of Datalog Materialisations

To efficiently answer queries, datalog systems often materialise all con...

Please sign up or login with your details

Forgot password? Click here to reset