Agents
Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities
In fact, the interaction of these two aspects requires addressing the fact that each agent's own safety constraint requires information from all others.
Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback
Our paper takes the first step to remove such assumptions.
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
Ofir Nachum, Yinlam Chow, Bo Dai, Lihong Li
Neural Information Processing Systems http://nips.cc/
Learning to Influence Human Behavior with Offline Reinforcement Learning
When interacting with people, AI agents do not just influence the state of the world - they also influence the actions people take in response to the agent, and even their underlying intentions and strategies.
