Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

by   Arthur Juliani, et al.

The rapid pace of research in Deep Reinforcement Learning has been driven by the presence of fast and challenging simulation environments. These environments often take the form of games; with tasks ranging from simple board games, to classic home console games, to modern strategy games. We propose a new benchmark called Obstacle Tower: a high visual fidelity, 3D, 3rd person, procedurally generated game environment. An agent in the Obstacle Tower must learn to solve both low-level control and high-level planning problems in tandem while learning from pixels and a sparse reward signal. Unlike other similar benchmarks such as the ALE, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment. In this paper we outline the environment and provide a set of initial baseline results produced by current state-of-the-art Deep RL methods as well as human players. In all cases these algorithms fail to produce agents capable of performing anywhere near human level on a set of evaluations designed to test both memorization and generalization ability. As such, we believe that the Obstacle Tower has the potential to serve as a helpful Deep RL benchmark now and into the future.


Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Recent progress in artificial intelligence through reinforcement learnin...

Learning Generalizable Behavior via Visual Rewrite Rules

Though deep reinforcement learning agents have achieved unprecedented su...

Planning from Pixels in Environments with Combinatorially Hard Search Spaces

The ability to form complex plans based on raw visual input is a litmus ...

PPO Dash: Improving Generalization in Deep Reinforcement Learning

Deep reinforcement learning is prone to overfitting, and traditional ben...

Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer

An important goal of research in Deep Reinforcement Learning in mobile r...

Rapid Task-Solving in Novel Environments

When thrust into an unfamiliar environment and charged with solving a se...

The Sandbox Environment for Generalizable Agent Research (SEGAR)

A broad challenge of research on generalization for sequential decision-...

Please sign up or login with your details

Forgot password? Click here to reset