Agents
Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization Xiangsen Wang
Despite some success in the single-agent setting, offline multi-agent RL (MARL) remains to be a challenge. The large joint state-action space and the coupled multi-agent behaviors pose extra complexities for offline policy optimization.
Conservative Offline Policy Adaptation in Multi-Agent Games
We prove that CSP learns a near-optimal risk-free offline adaptation policy upon convergence.
A Definition of Continual Reinforcement Learning
In a standard view of the reinforcement learning problem, an agent's goal is to efficiently identify a policy that maximizes long-term reward.
On the Interplay between Social Welfare and Tractability of Equilibria
Nash equilibria can be effectively addressed.
Mechanism Design for Collaborative Normal Mean Estimation
However, simply pooling everyone's data and sharing with each other can lead to free-riding [