conftrace_

trust-region learning

2 papers

Explore in graph

Also known as

TRL

Co-occurring keywords · papers mentioning both

mirror learning (2) general policy improvement (1) heterogeneous-agent reinforcement learning (1) advantage decomposition (1) policy optimisation (1) theoretical framework (1) monotonic improvement (1) trust region optimization (1) heterogeneous agent (1) convergence guarantee (1)

Papers

Heterogeneous-Agent Reinforcement Learning JMLR 2024 Mirror Learning: A Unifying Framework of Policy Optimisation ICML 2022