Model Releases
Constrained Multi-Agent Reinforcement Learning in Imagination
arXiv:2610.21319v1 Announce Type: new Abstract: Predicting cost in a multi-agent world model moves most constrained policy updates into imagination: the stronger model-free baseline needs 10 to 20 tim
arXiv:2610.21319v1 Announce Type: new Abstract: Predicting cost in a multi-agent world model moves most constrained policy updates into imagination: the stronger model-free baseline needs 10 to 20 times CA-MAMBA's interactions on the median SMAC configuration, and CA-MAMBA earns 2.8 to 12 times the baselines' MAMuJoCo reward at equal budget. In controlled tests on one task per benchmark, pricing the model's cost advantages at parity more than halves a cost-blind learner's cost and meets a tight continuous-control limit the learned multiplier misses, suggesting the model's cost estimates are not the bottleneck.
Related
- Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
- Safe Equilibrium Policy Optimization for Strategic Agent Policies
- Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows
Source: arXiv cs.AI | 2026-10-16