← Authors

Marcello Restelli

89 papers · 2007–2025 · 9 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (22) 🌈 Renaissance Researcher (6) 🐝 Cross-Pollinator (7) πŸƒ Academic Marathon (18) 🌍 Conference Polyglot (9) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌟 Keyword Trendsetter Combo (5) 🏠 Conference Loyalist (24) 🧬 Topic Evolution 🀝 Dynamic Duo (42) πŸ† Grand Slam πŸ‘₯ Mega-Team (22) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (40) πŸ† Keyword Champion (4) ⚑ Prolific Year (13) πŸ—ƒοΈ Keyword Collector (86) πŸ“ˆ Trend Setter πŸ’Ž Century Club (89) πŸ”₯ Unstoppable (10) ❓ The Questioner πŸš€ Conference Pioneer

Conferences

ICML (26) NIPS (24) AAAI (14) AISTATS (9) JMLR (6) ICLR (3) IJCAI (3) UAI (3) COLT (1)

Top co-authors

Alberto Maria Metelli (42) Matteo Papini (14) Mirco Mutti (13) Matteo Pirotta (12) Andrea Tirinzoni (11) Davide Maran (8) Alessandro Lazaric (7) Giorgia Ramponi (7) Riccardo Poiani (7) Marco Mussi (6)

Research topics

Reinforcement Learning (1) Statistics (1)

Keywords

reinforcement learning (23) regret bound (13) policy gradient (11) policy optimization (9) online learning (9) sample complexity (9) importance sampling (8) markov decision process (8) inverse reinforcement learning (7) multi-armed bandit (6) transfer learning (6) reward function (6) regret minimization (5) policy learning (5) imitation learning (5) function approximation (4) off-policy learning (4) continuous control (4) sequential decision-making (4) online algorithm (4)

Papers

Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story ICML 2025
Achieving $\widetilde\mathcalO(\sqrtT)$ Regret in Average-Reward POMDPs with Known Observation Models AISTATS 2025
Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning AISTATS 2025
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning NIPS 2024
Optimal Multi-Fidelity Best-Arm Identification NIPS 2024
Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs COLT 2024
Autoregressive Bandits AISTATS 2024
Parameterized Projected Bellman Operator AAAI 2024
How to Explore with Belief: State Entropy Maximization in POMDPs ICML 2024
Best Arm Identification for Stochastic Rising Bandits ICML 2024
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning ICLR 2024
Factored-Reward Bandits with Intermediate Observations ICML 2024
Information Capacity Regret Bounds for Bandits with Mediator Feedback JMLR 2024
No-Regret Reinforcement Learning in Smooth MDPs ICML 2024
Graph-Triggered Rising Bandits ICML 2024
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics NIPS 2024
Online Markov Decision Processes Configuration with Continuous Decision Space AAAI 2024
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs NIPS 2024
Bandits with Ranking Feedback NIPS 2024
Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control AAAI 2023
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization AAAI 2023
Simultaneously Updating All Persistence Values in Reinforcement Learning AAAI 2023
Dynamic Pricing with Volume Discounts in Online Settings AAAI 2023
Truncating Trajectories in Monte Carlo Reinforcement Learning ICML 2023
Dynamical Linear Bandits ICML 2023
Towards Theoretical Understanding of Inverse Reinforcement Learning ICML 2023
On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation UAI 2023
Convex Reinforcement Learning in Finite Trials JMLR 2023
Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach NIPS 2023
Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning NIPS 2023
A Tale of Sampling and Estimation in Discounted Reinforcement Learning AISTATS 2023
Tight Performance Guarantees of Imitator Policies with Continuous Actions AAAI 2023
Stochastic Rising Bandits ICML 2022
Challenging Common Assumptions in Convex Reinforcement Learning NIPS 2022
Multi-Fidelity Best-Arm Identification NIPS 2022
Off-Policy Evaluation with Deficient Support Using Side Information NIPS 2022
Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization AAAI 2022
Unsupervised Reinforcement Learning in Multiple Environments AAAI 2022
Reward-Free Policy Space Compression for Reinforcement Learning AISTATS 2022
Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning AISTATS 2022
Goal-Directed Planning via Hindsight Experience Replay ICLR 2022
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning ICML 2022
Delayed Reinforcement Learning by Imitation ICML 2022
The Importance of Non-Markovianity in Maximum State Entropy Exploration ICML 2022
Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts IJCAI 2022
Learning in Markov games: Can we exploit a general-sum opponent? UAI 2022
Meta-Reinforcement Learning by Tracking Task Non-stationarity IJCAI 2021
Gaussian Approximation for Bias Reduction in Q-Learning JMLR 2021
Learning in Non-Cooperative Configurable Markov Decision Processes NIPS 2021
Provably Efficient Learning of Transferable Rewards ICML 2021
Leveraging Good Representations in Linear Contextual Bandits ICML 2021
Time-variant variational transfer for value functions UAI 2021
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection NIPS 2021
Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning NIPS 2021
Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach JMLR 2021
MushroomRL: Simplifying Reinforcement Learning Research JMLR 2021
Newton Optimization on Helmholtz Decomposition for Continuous Games AAAI 2021
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate AAAI 2021
Policy Optimization as Online Learning with Mediator Feedback AAAI 2021
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits NIPS 2020
Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning ICML 2020
Sequential Transfer in Reinforcement Learning with a Generative Model ICML 2020
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies AAAI 2020
Importance Sampling Techniques for Policy Optimization JMLR 2020
Risk-Averse Trust Region Optimization for Reward-Volatility Reduction IJCAI 2020
Sharing Knowledge in Multi-Task Deep Reinforcement Learning ICLR 2020
Gradient-Aware Model-Based Policy Search AAAI 2020
Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration AISTATS 2020
Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions AISTATS 2020
A Novel Confidence-Based Algorithm for Structured Bandits AISTATS 2020
Inverse Reinforcement Learning from a Gradient-based Learner NIPS 2020
Transfer of Samples in Policy Search via Multiple Importance Sampling ICML 2019
Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters NIPS 2019
Reinforcement Learning in Configurable Continuous Environments ICML 2019
Optimistic Policy Optimization via Multiple Importance Sampling ICML 2019
Stochastic Variance-Reduced Policy Gradient ICML 2018
Configurable Markov Decision Processes ICML 2018
Policy Optimization via Importance Sampling NIPS 2018
Transfer of Value Functions via Variational Methods NIPS 2018
Importance Weighted Transfer of Samples in Reinforcement Learning ICML 2018
Adaptive Batch Size for Safe Policy Gradients NIPS 2017
Compatible Reward Inverse Reinforcement Learning NIPS 2017
Boosted Fitted Q-Iteration ICML 2017
Estimating Maximum Expected Value through Gaussian Approximation ICML 2016
Sparse Multi-Task Reinforcement Learning NIPS 2014
Safe Policy Iteration ICML 2013
Adaptive Step-Size for Policy Gradient Methods NIPS 2013
Transfer from Multiple MDPs NIPS 2011
Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods NIPS 2007