Katia Sycara

Interpretable Learned Emergent Communication for Human-Agent Teams

2022 · arXiv (Cornell University)

Learning interpretable communication is essential for multi-agent and human-agent teams (HATs). In multi-agent reinforcement learning for partially-observable environments, agents may convey information to others via learned communication, allowing the team to complete its task. Inspired …

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 …