conftrace_

policy mirror descent

7 papers

Explore in graph

Also known as

PMD

Co-occurring keywords

markov decision process (790) sample complexity (1169) linear convergence (158) mirror descent (148) policy gradient (520) average reward (29) convergence rate (607) policy optimization (657) reinforcement learning (4352) multi-step greedy policy (1)

Papers

Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds JMLR 2024
Policy Optimization for Robust Average Reward MDPs NIPS 2024
Operator World Models for Reinforcement Learning NIPS 2024
Policy Mirror Descent with Lookahead NIPS 2024
Inverse Reinforcement Learning with the Average Reward Criterion NIPS 2023
Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes NIPS 2023
On the Convergence Rates of Policy Gradient Methods JMLR 2022