arXiv cs.MA· Jiming Su, Feng Zhu, Yuhao Xiao, Miao Zhang·· 11 小时前AI 评分26
SEER：面向多智能体强化学习环境并行执行的可扩展事件驱动运行时
SEER: A Scalable Event-Driven Runtime for Parallel Execution of Multi-Agent Reinforcement Learning Environments
AI 导读
SEER 是一个面向多智能体强化学习环境执行的事件驱动运行时，将每个环境 step 建模为带时间戳的有界事件流，在保持串行等价边界输出的前提下并行执行独立事件。
正文 · 原文
Abstract: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 on GPUs, but the CPU-side environment path still updates entity states, resolves local interactions, and builds observations inside each $\mathrm{this http URL}$. This path can dominate latency in interaction-intensive workloads after policy batching. Existing vectorized environment interfaces and general event-driven runtimes do not directly address the fine-grained cross-entity work inside one bounded MARL step while preserving the step-level semantics expected by learning systems. We present SEER (Scalable Event-Driven Environment Runtime), a runtime for MARL environment execution under an explicit event-locality contract. SEER models each environment step as a bounded stream of timestamped events. If direct state updates are entity-local and cross-entity effects are represented as ordered future events, SEER can run independent events in parallel while preserving serial-equivalent boundary outputs. To make this contract practical, SEER uses a CAS-based dual-layer event queue: local event queues preserve per-entity causal order, while a parallel executive list exposes ready work to global worker threads. SEER further uses STPA, a preflight-guided thread-pool selection mechanism that combines short runtime traces with static workload and hardware features. We evaluate SEER on two parameterized MARL workloads: compute-intensive UAV swarm control (Aircraft) and communication-intensive wireless management (PCS). On Aircraft, SEER reduces inference latency by 16.2\% over the baseline. On PCS, SEER reduces environment-execution latency by 46.9\%, 19.5\%, and 64.9\% over ROSS-T, NBSE, and ROOT-Sim, respectively.
| Subjects: | Distributed, Parallel, and Cluster Computing (cs.DC); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.07996 [cs.DC] |
| (or arXiv:2611.07996v1 [cs.DC] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07996 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiming Su [view email]
[v1]
Thu, 5 Nov 2026 13:24:57 UTC (5,544 KB)
来源：arXiv cs.MA · arxiv.org