58 citations · 98 across the 6 of their papers we have counts for
6 papers
Improved Analysis of UCRL2 with Empirical Bernstein Inequality
Ronan Fruit, Matteo Pirotta, Alessandro Lazaric
We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For…
Concentration Inequalities for Multinoulli Random Variables
Jian Qian, Ronan Fruit, Matteo Pirotta +1
We investigate concentration inequalities for Dirichlet and Multinomial random variables.
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…
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…
Exploration--Exploitation in MDPs with Options
Ronan Fruit, Alessandro Lazaric
While a large body of empirical results show that temporally-extended actions and options may significantly affect the learning performance of an agent, the theoretical understandi…