On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning

no code implementations • 11 Apr 2024 • Giuseppe Canonaco, Leo Ardon, Alberto Pozanco, Daniel Borrajo

The use of Potential Based Reward Shaping (PBRS) has shown great promise in the ongoing research effort to tackle sample inefficiency in Reinforcement Learning (RL).

Reinforcement Learning (RL)

Time-Variant Variational Transfer for Value Functions

no code implementations • 26 May 2020 • Giuseppe Canonaco, Andrea Soprani, Manuel Roveri, Marcello Restelli

In most of the transfer learning approaches to reinforcement learning (RL) the distribution over the tasks is assumed to be stationary.

reinforcement-learning Reinforcement Learning (RL) +1

Stochastic Variance-Reduced Policy Gradient

1 code implementation • ICML 2018 • Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta, Marcello Restelli

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 (MDPs).