Agents
Continual Learning for Instruction Following from Realtime Feedback
We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy
Finding Friend and Foe in Multi-Agent Games
Jack Serrino, Max Kleiman-Weiner, David C. Parkes, Josh Tenenbaum
Neural Information Processing Systems http://nips.cc/
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals.
Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
Chao Qu, Shie Mannor, Huan Xu, Yuan Qi, Le Song, Junwu Xiong
Neural Information Processing Systems http://nips.cc/
Multiple Futures Prediction
Charlie Tang, Russ R. Salakhutdinov
Neural Information Processing Systems http://nips.cc/