conftrace_

relative entropy policy search

5 papers

Explore in graph

Also known as

REPS

Co-occurring keywords

policy search (87) policy optimization (657) reinforcement learning (4352) no-regret learning (67) bandit setting (16) regret bound (1926) convergence rate (607) adversarial markov decision process (6) saddle point optimization (11) prioritized exploration (1)

Papers

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