Agent57: Outperforming the Atari Human Benchmark
Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Oleksandr Vitvitskyi, Zhaohan Daniel Guo, Charles Blundell
2020International Conference on Machine Learning148 citations
Topics & Concepts
Benchmark (surveying)Computer scienceArtificial intelligenceGeographyCartographyReinforcement Learning in Robotics