output
20192022
most citedWhat Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study

107 citations

Showing cs.LGShow all

16 papers · 1 filter

cs.LG2022

Entropy Regularized Reinforcement Learning with Cascading Networks

Riccardo Della Vecchia, Alena Shilova, Philippe Preux +1

Deep Reinforcement Learning (Deep RL) has had incredible achievements on high dimensional problems, yet its learning process remains unstable even on the simplest tasks. Deep RL us…

cs.LG2022

Soft Action Priors: Towards Robust Policy Transfer

Matheus Centa, Philippe Preux

Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to age…

cs.LG20221 cited

When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits

Achraf Azize, Debabrota Basu

We study the problem of multi-armed bandits with -global Differential Privacy (DP). First, we prove the minimax and problem-dependent regret lower bounds for stochastic and line…

cs.LG2022

Optimistic PAC Reinforcement Learning: the Instance-Dependent View

Andrea Tirinzoni, Aymen Al-Marjani, Emilie Kaufmann

Optimistic algorithms have been extensively studied for regret minimization in episodic tabular MDPs, both from a minimax and an instance-dependent view. However, for the PAC RL pr…

cs.LG2022

Efficient Algorithms for Extreme Bandits

Dorian Baudry, Yoan Russac, Emilie Kaufmann

In this paper, we contribute to the Extreme Bandit problem, a variant of Multi-Armed Bandits in which the learner seeks to collect the largest possible reward. We first study the c…

cs.LG20212 cited

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano +3

We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. We first de…