← Keywords

sample complexity

1158 papers

Explore in graph

Co-occurring keywords

reinforcement learning (4122) pac learning (280) multi-armed bandit (1091) markov decision process (788) learning theory (518) differential privacy (1010) stochastic optimization (1060) neural network (6616) active learning (1295) regret bound (1918)

Papers

Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs ICML 2021
On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification AISTATS 2021
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play ICML 2021
Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning ICML 2021
Predicting What You Already Know Helps: Provable Self-Supervised Learning NIPS 2021
A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning ICML 2021
Don’t Do What Doesn’t Matter: Intrinsic Motivation with Action Usefulness IJCAI 2021
Towards Tight Bounds on the Sample Complexity of Average-reward MDPs ICML 2021
Pure Exploration in Kernel and Neural Bandits NIPS 2021
Bilinear Classes: A Structural Framework for Provable Generalization in RL ICML 2021
Model-Based Reinforcement Learning for Infinite-Horizon Discounted Constrained Markov Decision Processes IJCAI 2021
Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems NIPS 2021
A Theoretical Analysis of Fine-tuning with Linear Teachers NIPS 2021
Optimal Algorithms for Range Searching over Multi-Armed Bandits IJCAI 2021
Provable Meta-Learning of Linear Representations ICML 2021
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning NIPS 2021
Sample Efficient Decentralized Stochastic Frank-Wolfe Methods for Continuous DR-Submodular Maximization IJCAI 2021
Minimax sample complexity for turn-based stochastic game UAI 2021
Fast Pure Exploration via Frank-Wolfe NIPS 2021
Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification NIPS 2021
Variance-dependent best arm identification UAI 2021
The Sample Complexity of Teaching by Reinforcement on Q-Learning AAAI 2021
State-Wise Adaptive Discounting from Experience (SADE): A Novel Discounting Scheme for Reinforcement Learning (Student Abstract) AAAI 2021
Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination NIPS 2021
Efficient Bayesian network structure learning via local Markov boundary search NIPS 2021