conftrace_

regret bound

1926 papers

Explore in graph

Also known as

RB

Co-occurring keywords

online learning (1777) multi-armed bandit (1098) contextual bandit (381) stochastic optimization (1060) reinforcement learning (4352) online algorithm (445) upper confidence bound (197) markov decision process (790) thompson sampling (237) online convex optimization (165)

Papers

A One-Size-Fits-All Solution to Conservative Bandit Problems AAAI 2021
Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits AAAI 2021
Multinomial Logit Contextual Bandits: Provable Optimality and Practicality AAAI 2021
Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation AAAI 2021
Robust Bandit Learning with Imperfect Context AAAI 2021
Sample Efficient Reinforcement Learning with REINFORCE AAAI 2021
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory AAAI 2021
Robustness Guarantees for Mode Estimation with an Application to Bandits AAAI 2021
Variational Bayesian Reinforcement Learning with Regret Bounds NIPS 2021
RL for Latent MDPs: Regret Guarantees and a Lower Bound NIPS 2021
Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses NIPS 2021
Learning in Non-Cooperative Configurable Markov Decision Processes NIPS 2021
Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs NIPS 2021
The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition NIPS 2021
Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning NIPS 2021
Provably efficient multi-task reinforcement learning with model transfer NIPS 2021
Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning NIPS 2021
Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints NIPS 2021
Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning NIPS 2021
A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning NIPS 2021
BooVI: Provably Efficient Bootstrapped Value Iteration NIPS 2021
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret NIPS 2021
Bellman-consistent Pessimism for Offline Reinforcement Learning NIPS 2021
Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP NIPS 2021
A Biased Graph Neural Network Sampler with Near-Optimal Regret NIPS 2021