After six months of competition (and a few last-minute submissions), we are happy to announce the conclusion and winners of the Obstacle Tower Challenge. We want to thank all of the participants for both rounds and congratulate Alex Nichol, the Compscience.org We are also excited to share that we have open-sourced Obstacle Tower for the research community to extend for their own needs. We started this challenge in February as a way to help foster research in the AI community, by providing a challenging new benchmark of agent performance built in Unity, which we called Obstacle Tower. The Obstacle Tower was developed to be difficult for current machine learning algorithms to solve, and push the boundaries of what was possible in the field by focusing on procedural generation. Key to that was only allowing participants access to one hundred instances of the Obstacle Tower, and evaluating their trained agents on a set of unique procedurally generated towers they had never seen before.

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.

We consider the problem of planning, on the fly, a path whereby a robotic vehicle will cover every point in an initially unknown spatial environment. We describe four strategies (Iterated WaveFront, Greedy-Scan, Delayed Greedy-Scan and Closest-First Scan) for generating cost-effective coverage plans in real time for unknown environments. We give theorems showing the correctness of our planning strategies. Our experiments demonstrate that some of these strategies work significantly better than others, and that the best ones work very well; e.g., in environments having an average of 64,000 locations for the robot to cover, the best strategy returned plans with less than 6% redundant coverage, and took only an average of 0.1 milliseconds per action.