Deep reinforcement learning is prone to overfitting, and traditional benchmarks such as Atari 2600 benchmark can exacerbate this problem. The Obstacle Tower Challenge addresses this by using randomized environments and separate seeds for training, validation, and test runs. This paper examines various improvements and best practices to the PPO algorithm using the Obstacle Tower Challenge to empirically study their impact with regards to generalization. Our experiments show that the combination provides state-of-the-art performance on the Obstacle Tower Challenge.

Unity Technologies has a new game that you can't play. The maker of game development tools is releasing a new title called Obstacle Tower that is designed to challenge the capabilities of artificial intelligence. The release of the title is being accompanied by a contest, the Obstacle Tower Challenge, that will allow participants to run their AI agents through the 100-level challenge and compete for prizes. According to Unity, Obstacle Tower provides a game-like environment for machine learning researchers to play around with and fine-tune their AI. The tower operates similarly to a standard platforming game.

Unity Technologies has teamed up with Google Cloud Platform to create the Obstacle Tower Challenge, which will test the limits of artificial intelligence in games. In the first-of-its-kind contest, Google will offer a prize of cash, travel vouchers, and Google Cloud Platform credits, valued at more than $100,000. Unity, the maker of the Unity game engine, is creating the contest to test the capabilities of intelligent agents and accelerate the research and development of AI. (Unity recently got in a spat with Improbable over a licensing dispute.) The Obstacle Tower Challenge will be a new benchmark aimed at testing the vision, control, planning, and generalization abilities of AI systems -- capabilities that no other benchmark has tested together before. Above: The Obstacle Tower Challenge offers $100,000 in prizes.