Ryan Hope

Challenges of Context and Time in Reinforcement Learning: Introducing\n Space Fortress as a Benchmark

2018 · arXiv (Cornell University)

Research in deep reinforcement learning (RL) has coalesced around improving\nperformance on benchmarks like the Arcade Learning Environment. However, these\nbenchmarks conspicuously miss important characteristics like abrupt\ncontext-dependent shifts in strategy and temporal sensitivity that are often\npresent in …