Test-Time Regret Minimization in Meta Reinforcement Learning von Mutti, Mirco, Tamar, Aviv

Volltext bestellen

How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach von Lazzati, Filippo, Mutti, Mirco, Metelli, Alberto Maria

Volltext bestellen

Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms von Lazzati, Filippo, Mutti, Mirco, Metelli, Alberto Maria

Volltext bestellen

Test-Time Regret Minimization in Meta Reinforcement Learning von Mutti, Mirco, Aviv Tamar

Volltext

A Tale of Sampling and Estimation in Discounted Reinforcement Learning von Metelli, Alberto Maria, Mutti, Mirco, Restelli, Marcello

Volltext bestellen

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough von Zamboni, Riccardo, Cirino, Duilio, Restelli, Marcello, Mutti, Mirco

Volltext bestellen

How to Explore with Belief: State Entropy Maximization in POMDPs von Zamboni, Riccardo, Cirino, Duilio, Restelli, Marcello, Mutti, Mirco

Volltext bestellen

An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies von Mutti, Mirco, Restelli, Marcello

Volltext bestellen

A Theoretical Framework for Partially Observed Reward-States in RLHF von Kausik, Chinmaya, Mutti, Mirco, Pacchiano, Aldo, Tewari, Ambuj

Volltext bestellen

Reward-Free Policy Space Compression for Reinforcement Learning von Mutti, Mirco, Del Col, Stefano, Restelli, Marcello

Volltext bestellen

The Importance of Non-Markovianity in Maximum State Entropy Exploration von Mutti, Mirco, De Santi, Riccardo, Restelli, Marcello

Volltext bestellen

Unsupervised Reinforcement Learning in Multiple Environments von Mutti, Mirco, Mancassola, Mattia, Restelli, Marcello

Volltext bestellen

Persuading Farsighted Receivers in MDPs: the Power of Honesty von Bernasconi, Martino, Castiglioni, Matteo, Marchesi, Alberto, Mutti, Mirco

Volltext bestellen

Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction von De Santi, Riccardo, Joseph, Federico Arangath, Liniger, Noah, Mutti, Mirco, Krause, Andreas

Volltext bestellen

How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach von Lazzati, Filippo, Mutti, Mirco, Metelli, Alberto Maria

Volltext

Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate von Mutti, Mirco, Pratissoli, Lorenzo, Restelli, Marcello

Volltext bestellen

Challenging Common Assumptions in Convex Reinforcement Learning von Mutti, Mirco, De Santi, Riccardo, De Bartolomeis, Piersilvio, Restelli, Marcello

Volltext bestellen

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning von Mutti, Mirco, De Santi, Riccardo, Restelli, Marcello, Marx, Alexander, Ramponi, Giorgia

Volltext bestellen

Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms von Lazzati, Filippo, Mutti, Mirco, Metelli, Alberto Maria

Volltext

A Tale of Sampling and Estimation in Discounted Reinforcement Learning von Metelli, Alberto Maria, Mutti, Mirco, Restelli, Marcello

Volltext