Skip to content
conftrace_

relative entropy policy search

5 papers

Explore in graph

Also known as

REPS

Co-occurring keywords · papers mentioning both

policy search (2) policy optimization (2) reinforcement learning (2) no-regret learning (1) bandit setting (1) regret bound (1) convergence rate (1) adversarial markov decision process (1) saddle point optimization (1) prioritized exploration (1)

Papers

Dimensionality Reduction and Prioritized Exploration for Policy Search AISTATS 2022 Logistic Q-Learning AISTATS 2021 Near Optimal Policy Optimization via REPS NeurIPS 2021 No-regret learning with high-probability in adversarial Markov decision processes UAI 2021 Online learning in episodic Markovian decision processes by relative entropy policy search NeurIPS 2013