Reinforcement Learning
LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
General decision intelligence needs to solve tasks in many distinct domains.
SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning Benjamin Ellis 1 Jonathan Cook
We show that these changes ensure the benchmark requires the use of closed-loop policies.
Multi-Player Zero-Sum Markov Games with Networked Separable Interactions Chanwoo Park
CCE collapses to the NE in such games when the payoffs are zero-sum.
Deep Reinforcement Learning with Plasticity Injection
The applications of this intervention are two-fold: first, as a diagnostic tool -- if injection increases the performance, we may conclude that an agent's network was losing its plasticity.
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.