DeepAI AI Chat
Log In Sign Up

Reinforcement Learning for the Soccer Dribbling Task

by   Arthur Carvalho, et al.
University of Waterloo

We propose a reinforcement learning solution to the soccer dribbling task, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best action to take at each decision point. After defining meaningful variables to represent the state space, and high-level macro-actions to incorporate domain knowledge, we describe our application of the reinforcement learning algorithm Sarsa with CMAC for function approximation. Our experiments show that, after the training period, the dribbler is able to accomplish its task against a strong adversary around 58 of the time.


page 1

page 5

page 6


Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder

One problem in the application of reinforcement learning to real-world p...

Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks

This paper discusses a system that accelerates reinforcement learning by...

Reinforcing Classical Planning for Adversary Driving Scenarios

Adversary scenarios in driving, where the other vehicles may make mistak...

DinerDash Gym: A Benchmark for Policy Learning in High-Dimensional Action Space

It has been arduous to assess the progress of a policy learning algorith...

Provable Defense against Backdoor Policies in Reinforcement Learning

We propose a provable defense mechanism against backdoor policies in rei...

Backdoor Attacks on Multiagent Collaborative Systems

Backdoor attacks on reinforcement learning implant a backdoor in a victi...