conftrace_

mirror learning

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

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

Papers

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