Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations

05/22/2023
by   Keisuke Fujii, et al.
0

Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generate flexible and diverse behaviors in cyberspace; however, when modeling real-world biological multi-agents, there is a domain gap between behaviors in the source (i.e., real-world data) and the target (i.e., cyberspace for RL), and the source environment parameters are usually unknown. In this paper, we propose a method for adaptive action supervision in RL from real-world demonstrations in multi-agent scenarios. We adopt an approach that combines RL and supervised learning by selecting actions of demonstrations in RL based on the minimum distance of dynamic time warping for utilizing the information of the unknown source dynamics. This approach can be easily applied to many existing neural network architectures and provide us with an RL model balanced between reproducibility as imitation and generalization ability to obtain rewards in cyberspace. In the experiments, using chase-and-escape and football tasks with the different dynamics between the unknown source and target environments, we show that our approach achieved a balance between the reproducibility and the generalization ability compared with the baselines. In particular, we used the tracking data of professional football players as expert demonstrations in football and show successful performances despite the larger gap between behaviors in the source and target environments than the chase-and-escape task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/01/2021

Multi-Agent Transfer Learning in Reinforcement Learning-Based Ride-Sharing Systems

Reinforcement learning (RL) has been used in a range of simulated real-w...
research
02/24/2021

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

We study reinforcement learning (RL) with no-reward demonstrations, a se...
research
02/15/2021

Data-driven Analysis for Understanding Team Sports Behaviors

Understanding the principles of real-world biological multi-agent behavi...
research
05/08/2023

DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety

Deploying reinforcement learning agents in the real world can be challen...
research
05/11/2022

Characterizing the Action-Generalization Gap in Deep Q-Learning

We study the action generalization ability of deep Q-learning in discret...
research
10/05/2021

OTTR: Off-Road Trajectory Tracking using Reinforcement Learning

In this work, we present a novel Reinforcement Learning (RL) algorithm f...
research
07/07/2020

Policy learning with partial observation and mechanical constraints for multi-person modeling

Extracting the rules of real-world biological multi-agent behaviors is a...

Please sign up or login with your details

Forgot password? Click here to reset