2 papers
cs.DC2026
SEER: A Scalable Event-Driven Runtime for Parallel Execution of Multi-Agent Reinforcement Learning Environments
Jiming Su, Feng Zhu, Yuhao Xiao +1
Multi-agent reinforcement learning (MARL) is increasingly used in systems where many entities interact in a shared environment. In these workloads, policy inference can be batched…
cs.LG2026
Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference
Jiming Su, Hantao Hua, Lujia Yin +2
In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynam…