58 citations · 284 across the 49 of their papers we have counts for
5 papers · 1 filter
Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes
Jian Qian, Ronan Fruit, Matteo Pirotta +1
We introduce and analyse two algorithms for exploration-exploitation in discrete and continuous Markov Decision Processes (MDPs) based on exploration bonuses. SCAL is a variant…
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes
Ronan Fruit, Matteo Pirotta, Alessandro Lazaric
While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and p…
Stochastic Variance-Reduced Policy Gradient
Matteo Papini, Damiano Binaghi, Giuseppe Canonaco +2
In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MD…
Importance Weighted Transfer of Samples in Reinforcement Learning
Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta +1
We consider the transfer of experience samples (i.e., tuples < s, a, s', r >) in reinforcement learning (RL), collected from a set of source tasks to improve the learning process i…
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning
Ronan Fruit, Matteo Pirotta, Alessandro Lazaric +1
We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov decision process (MDP) for which an upper bound $c…