Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games

by   Philip Bontrager, et al.
Maastricht University
NYU college
University of Strathclyde

Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to game-playing agents. These games are implemented in the General Video Game AI framework, which allows us to compare the behavior of reinforcement learning-based agents with planning agents based on tree search. We find that several of these games reliably deceive deep reinforcement learners, and that the resulting behavior highlights the shortcomings of the learning algorithm. The particular ways in which agents fail differ from how planning-based agents fail, further illuminating the character of these algorithms. We propose an initial typology of deceptions which could help us better understand pitfalls and failure modes of (deep) reinforcement learning.


page 3

page 4


Deep Reinforcement Learning for General Video Game AI

The General Video Game AI (GVGAI) competition and its associated softwar...

Deep Reinforcement Learning for Playing 2.5D Fighting Games

Deep reinforcement learning has shown its success in game playing. Howev...

Multi-Issue Bargaining With Deep Reinforcement Learning

Negotiation is a process where agents aim to work through disputes and m...

A Review of Uncertainty for Deep Reinforcement Learning

Uncertainty is ubiquitous in games, both in the agents playing games and...

On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer

Autonomously trained agents that are supposed to play video games reason...

A Framework for Constrained and Adaptive Behavior-Based Agents

Behavior Trees are commonly used to model agents for robotics and games,...

Robust Dual View Deep Agent

Motivated by recent advance of machine learning using Deep Reinforcement...

Please sign up or login with your details

Forgot password? Click here to reset