Learning to Request Guidance in Emergent Communication

12/11/2019
by   Benjamin Kolb, et al.
12

Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing the agent with discrete messages in an emerged language about how to solve the task. We extend this one-directional communication by a one-bit communication channel from the learner back to the guide: It is able to ask the guide for help, and we limit the guidance by penalizing the learner for these requests. During training, the agent learns to control this gate based on its current observation. We find that the amount of requested guidance decreases over time and guidance is requested in situations of high uncertainty. We investigate the agent's performance in cases of open and closed gates and discuss potential motives for the observed gating behavior.

READ FULL TEXT

page 3

page 7

page 12

page 16

research
08/14/2019

Mastering emergent language: learning to guide in simulated navigation

To cooperate with humans effectively, virtual agents need to be able to ...
research
09/21/2019

Leveraging Human Guidance for Deep Reinforcement Learning Tasks

Reinforcement learning agents can learn to solve sequential decision tas...
research
09/12/2021

Learning Selective Communication for Multi-Agent Path Finding

Learning communication via deep reinforcement learning (RL) or imitation...
research
03/05/2023

Vision based Virtual Guidance for Navigation

This paper explores the impact of virtual guidance on mid-level represen...
research
05/30/2019

Recent Advances in Imitation Learning from Observation

Imitation learning is the process by which one agent tries to learn how ...
research
12/14/2021

Learning to Guide and to Be Guided in the Architect-Builder Problem

We are interested in interactive agents that learn to coordinate, namely...
research
04/20/2018

Delegating via Quitting Games

Delegation allows an agent to request that another agent completes a tas...

Please sign up or login with your details

Forgot password? Click here to reset