conftrace_

linear mdp

34 papers

Explore in graph

Co-occurring keywords

reinforcement learning (4352) regret bound (1926) sample complexity (1169) function approximation (319) linear function approximation (101) value iteration (162) linear markov decision process (11) offline reinforcement learning (492) tabular mdp (14) sample efficiency (472)

Papers

Nearly Horizon-Free Offline Reinforcement Learning NIPS 2021
Bilinear Classes: A Structural Framework for Provable Generalization in RL ICML 2021
Logarithmic Regret for Reinforcement Learning with Linear Function Approximation ICML 2021
Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting NIPS 2021
Fast Rates for the Regret of Offline Reinforcement Learning COLT 2021
Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model NIPS 2021
Online Sparse Reinforcement Learning AISTATS 2021
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning NIPS 2020
Learning Near Optimal Policies with Low Inherent Bellman Error ICML 2020