no code implementations • 4 Feb 2023 • Pouya Hamadanian, Arash Nasr-Esfahany, Malte Schwarzkopf, Siddartha Sen, Mohammad Alizadeh
We present Locally Constrained Policy Optimization (LCPO), an online RL approach that combats CF by anchoring policy outputs on old experiences while optimizing the return on current experiences.
no code implementations • 14 Jan 2022 • Pouya Hamadanian, Malte Schwarzkopf, Siddartha Sen, Mohammad Alizadeh
Such agents must explore and learn new environments, without hurting the system's performance, and remember them over time.