PAC: AssistedValueFactorisationwithCounterfactual PredictionsinMulti-AgentReinforcementLearning

Feb-9-2026, 11:20:00 GMT–Neural Information Processing Systems

To enable decentralized execution, we alsoderivefactorized per-agentpolicies inspired byamaximum-entropyMARL framework.

artificial intelligence, machine learning, reinforcement learning, (17 more...)

Neural Information Processing Systems

Feb-9-2026, 11:20:00 GMT

Conferences PDF

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Reinforcement Learning (0.96)
  - Representation & Reasoning > Agents (1.00)