Matteo Pirotta

20

Papers

84

Total Citations

Papers (20)

Adaptive Batch Size for Safe Policy Gradients

Regret Minimization in MDPs with Options without Prior Knowledge

Compatible Reward Inverse Reinforcement Learning

NeurIPS 2017arXiv

Temporal Difference Flows

Simple Ingredients for Offline Reinforcement Learning

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs

Adversarial Attacks on Linear Contextual Bandits

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret

A Provably Efficient Sample Collection Strategy for Reinforcement Learning

Local Differential Privacy for Regret Minimization in Reinforcement Learning

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees

Boosted Fitted Q-Iteration

Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning

Stochastic Variance-Reduced Policy Gradient

Importance Weighted Transfer of Samples in Reinforcement Learning

Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes

Regret Bounds for Learning State Representations in Reinforcement Learning

Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits