Marcello Restelli

verfied profile

∙ 0 followers
Politecnico di Milano

Policy Optimization as Online Learning with Mediator Feedback

Policy Optimization (PO) is a widely used approach to address continuous...
12/15/2020 ∙ by Alberto Maria Metelli, et al. ∙ 3 ∙ share

read it
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits

In the contextual linear bandit setting, algorithms built on the optimis...
10/23/2020 ∙ by Andrea Tirinzoni, et al. ∙ 0 ∙ share

read it
Option Hedging with Risk Averse Reinforcement Learning

In this paper we show how risk-averse reinforcement learning can be used...
10/23/2020 ∙ by Edoardo Vittori, et al. ∙ 0 ∙ share

read it
Inverse Reinforcement Learning from a Gradient-based Learner

Inverse Reinforcement Learning addresses the problem of inferring an exp...
07/15/2020 ∙ by Giorgia Ramponi, et al. ∙ 0 ∙ share

read it
Newton-based Policy Optimization for Games

Many learning problems involve multiple agents optimizing different inte...
07/15/2020 ∙ by Giorgia Ramponi, et al. ∙ 0 ∙ share

read it
A Policy Gradient Method for Task-Agnostic Exploration

In a reward-free environment, what is a suitable intrinsic objective for...
07/09/2020 ∙ by Mirco Mutti, et al. ∙ 0 ∙ share

read it
Sequential Transfer in Reinforcement Learning with a Generative Model

We are interested in how to design reinforcement learning agents that pr...
07/01/2020 ∙ by Andrea Tirinzoni, et al. ∙ 0 ∙ share

read it
Time-Variant Variational Transfer for Value Functions

In most transfer learning approaches to reinforcement learning (RL) the ...
05/26/2020 ∙ by Giuseppe Canonaco, et al. ∙ 5 ∙ share

read it
A Novel Confidence-Based Algorithm for Structured Bandits

We study finite-armed stochastic bandits where the rewards of each arm m...
05/23/2020 ∙ by Andrea Tirinzoni, et al. ∙ 0 ∙ share

read it
Online Joint Bid/Daily Budget Optimization of Internet Advertising Campaigns

Pay-per-click advertising includes various formats (e.g., search, contex...
03/03/2020 ∙ by Alessandro Nuara, et al. ∙ 0 ∙ share

read it
Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning

The choice of the control frequency of a system has a relevant impact on...
02/17/2020 ∙ by Alberto Maria Metelli, et al. ∙ 0 ∙ share

read it
MushroomRL: Simplifying Reinforcement Learning Research

MushroomRL is an open-source Python library developed to simplify the pr...
01/04/2020 ∙ by Carlo D'Eramo, et al. ∙ 0 ∙ share

read it
Risk-Averse Trust Region Optimization for Reward-Volatility Reduction

In real-world decision-making problems, for instance in the fields of fi...
12/06/2019 ∙ by Lorenzo Bisi, et al. ∙ 0 ∙ share

read it
Gradient-Aware Model-based Policy Search

Traditional model-based reinforcement learning approaches learn a model ...
09/09/2019 ∙ by Pierluca D'Oro, et al. ∙ 0 ∙ share

read it
Policy Space Identification in Configurable Environments

We study the problem of identifying the policy space of a learning agent...
09/09/2019 ∙ by Alberto Maria Metelli, et al. ∙ 0 ∙ share

read it
Feature Selection via Mutual Information: New Theoretical Insights

Mutual information has been successfully adopted in filter feature-selec...
07/17/2019 ∙ by Mario Beraha, et al. ∙ 0 ∙ share

read it
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies

What is a good exploration strategy for an agent that interacts with an ...
07/10/2019 ∙ by Mirco Mutti, et al. ∙ 0 ∙ share

read it
Smoothing Policies and Safe Policy Gradients

Policy gradient algorithms are among the best candidates for the much an...
05/08/2019 ∙ by Matteo Papini, et al. ∙ 0 ∙ share

read it
Policy Optimization via Importance Sampling

Policy optimization is an effective reinforcement learning approach to s...
09/17/2018 ∙ by Alberto Maria Metelli, et al. ∙ 0 ∙ share

read it
Stochastic Variance-Reduced Policy Gradient

In this paper, we propose a novel reinforcement- learning algorithm cons...
06/14/2018 ∙ by Matteo Papini, et al. ∙ 0 ∙ share

read it
Configurable Markov Decision Processes

In many real-world problems, there is the possibility to configure, to a...
06/14/2018 ∙ by Alberto Maria Metelli, et al. ∙ 0 ∙ share

read it
Importance Weighted Transfer of Samples in Reinforcement Learning

We consider the transfer of experience samples (i.e., tuples < s, a, s',...
05/28/2018 ∙ by Andrea Tirinzoni, et al. ∙ 0 ∙ share

read it
Cost-Sensitive Approach to Batch Size Adaptation for Gradient Descent

In this paper, we propose a novel approach to automatically determine th...
12/09/2017 ∙ by Matteo Pirotta, et al. ∙ 0 ∙ share

read it
Unimodal Thompson Sampling for Graph-Structured Arms

We study, to the best of our knowledge, the first Bayesian algorithm for...
11/17/2016 ∙ by Stefano Paladino, et al. ∙ 0 ∙ share

read it
Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation Supplementary Material

This document contains supplementary material for the paper "Multi-objec...
06/13/2014 ∙ by Matteo Pirotta, et al. ∙ 0 ∙ share

read it
Transfer from Multiple MDPs

Transfer reinforcement learning (RL) methods leverage on the experience ...
08/31/2011 ∙ by Alessandro Lazaric, et al. ∙ 0 ∙ share

read it

Marcello Restelli

Featured Co-authors

Jan Peters

Alessandro Lazaric

Nicola Gatti

Matteo Pirotta

Carlo D'Eramo

Matteo Papini

Alberto Maria Metelli

Andrea Tirinzoni

Mario Beraha

Davide Tateo

Simone Parisi

Policy Optimization as Online Learning with Mediator Feedback

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits

Option Hedging with Risk Averse Reinforcement Learning

Inverse Reinforcement Learning from a Gradient-based Learner

Newton-based Policy Optimization for Games

A Policy Gradient Method for Task-Agnostic Exploration

Sequential Transfer in Reinforcement Learning with a Generative Model

Time-Variant Variational Transfer for Value Functions

A Novel Confidence-Based Algorithm for Structured Bandits

Online Joint Bid/Daily Budget Optimization of Internet Advertising Campaigns

Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning

MushroomRL: Simplifying Reinforcement Learning Research

Risk-Averse Trust Region Optimization for Reward-Volatility Reduction

Gradient-Aware Model-based Policy Search

Policy Space Identification in Configurable Environments

Feature Selection via Mutual Information: New Theoretical Insights

An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies

Smoothing Policies and Safe Policy Gradients

Policy Optimization via Importance Sampling

Stochastic Variance-Reduced Policy Gradient

Configurable Markov Decision Processes

Importance Weighted Transfer of Samples in Reinforcement Learning

Cost-Sensitive Approach to Batch Size Adaptation for Gradient Descent

Unimodal Thompson Sampling for Graph-Structured Arms

Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation Supplementary Material

Transfer from Multiple MDPs