An Analytical Update Rule for General Policy Optimization

no code implementations • 3 Dec 2021 • Hepeng Li, Nicholas Clavette, Haibo He

We present an analytical policy update rule that is independent of parametric function approximators.

reinforcement-learning Reinforcement Learning (RL)

Multi-Agent Trust Region Policy Optimization

no code implementations • 15 Oct 2020 • Hepeng Li, Haibo He

By making a series of approximations to the consensus optimization model, we propose a decentralized MARL algorithm, which we call multi-agent TRPO (MATRPO).

Multi-agent Reinforcement Learning Privacy Preserving +2