Optimistic Agents are Asymptotically Optimal

09/29/2012
by   Peter Sunehag, et al.
0

We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic case we provide finite error bounds.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/27/2011

Asymptotically Optimal Agents

Artificial general intelligence aims to create agents capable of learnin...
research
02/25/2016

Thompson Sampling is Asymptotically Optimal in General Environments

We discuss a variant of Thompson sampling for nonparametric reinforcemen...
research
03/04/2019

Strong Asymptotic Optimality in General Environments

Reinforcement Learning agents are expected to eventually perform well. T...
research
06/05/2020

Curiosity Killed the Cat and the Asymptotically Optimal Agent

Reinforcement learners are agents that learn to pick actions that lead t...
research
07/26/2019

An asymptotically optimal transform of Pearson's correlation statistic

It is shown that for any correlation-parametrized model of dependence an...
research
09/18/2018

Optimal strategies for patrolling fences

A classical multi-agent fence patrolling problem asks: What is the maxim...
research
11/01/2019

Six constructions of asymptotically optimal codebooks via the character sums

In this paper, using additive characters of finite field, we find a code...

Please sign up or login with your details

Forgot password? Click here to reset