conftrace_

linear function approximation

101 papers

Explore in graph

Also known as

LFA

Co-occurring keywords

reinforcement learning (4352) regret bound (1926) markov decision process (790) sample complexity (1169) function approximation (319) temporal difference learning (149) value function (295) value iteration (162) policy optimization (657) policy evaluation (115)

Papers

Computational-Statistical Gap in Reinforcement Learning COLT 2022
Adaptive Multi-Goal Exploration AISTATS 2022
Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation ICML 2022
TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions ALT 2022
Provably Efficient Model-Free Constrained RL with Linear Function Approximation NIPS 2022
Proximal Point Imitation Learning NIPS 2022
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient ICML 2021
Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games ICML 2021
Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses NIPS 2021
Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach ICML 2021
Preferential Temporal Difference Learning ICML 2021
Safe Reinforcement Learning with Linear Function Approximation ICML 2021
On the Value of Interaction and Function Approximation in Imitation Learning NIPS 2021
Online learning in MDPs with linear function approximation and bandit feedback. NIPS 2021
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes COLT 2021
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions ALT 2021
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL ICML 2021
Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation NIPS 2021
Variance-Aware Off-Policy Evaluation with Linear Function Approximation NIPS 2021
Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints NIPS 2021
Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration NIPS 2021
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation AISTATS 2021
Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation NIPS 2021
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation COLT 2021
Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping ICML 2021