Delegating via Quitting Games

04/20/2018
by   Juan Afanador, et al.
0

Delegation allows an agent to request that another agent completes a task. In many situations the task may be delegated onwards, and this process can repeat until it is eventually, successfully or unsuccessfully, performed. We consider policies to guide an agent in choosing who to delegate to when such recursive interactions are possible. These policies, based on quitting games and multi-armed bandits, were empirically tested for effectiveness. Our results indicate that the quitting game based policies outperform those which do not explicitly account for the recursive nature of delegation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/13/2017

Combinatorial Multi-armed Bandits for Real-Time Strategy Games

Games with large branching factors pose a significant challenge for game...
research
06/30/2020

R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games

This paper presents a recursive reasoning formalism of Bayesian optimiza...
research
06/29/2018

Counting to Explore and Generalize in Text-based Games

We propose a recurrent RL agent with an episodic exploration mechanism t...
research
09/28/2021

Risk averse non-stationary multi-armed bandits

This paper tackles the risk averse multi-armed bandits problem when incu...
research
02/29/2016

Collaborative Learning of Stochastic Bandits over a Social Network

We consider a collaborative online learning paradigm, wherein a group of...
research
08/04/2021

Model-Based Opponent Modeling

When one agent interacts with a multi-agent environment, it is challengi...
research
12/11/2019

Learning to Request Guidance in Emergent Communication

Previous research into agent communication has shown that a pre-trained ...

Please sign up or login with your details

Forgot password? Click here to reset