Yonathan Efroni

is this you? claim profile

∙ 0 followers

Reinforcement Learning with Trajectory Feedback

The computational model of reinforcement learning is based upon the abil...
08/13/2020 ∙ by Yonathan Efroni, et al. ∙ 46 ∙ share

read it
Bandits with Partially Observable Offline Data

We study linear contextual bandits with access to a large, partially obs...
06/11/2020 ∙ by Guy Tennenholtz, et al. ∙ 0 ∙ share

read it
Mirror Descent Policy Optimization

We propose deep Reinforcement Learning (RL) algorithms inspired by mirro...
05/20/2020 ∙ by Manan Tomar, et al. ∙ 0 ∙ share

read it
Exploration-Exploitation in Constrained MDPs

In many sequential decision-making problems, the goal is to optimize a u...
03/04/2020 ∙ by Yonathan Efroni, et al. ∙ 0 ∙ share

read it
Optimistic Policy Optimization with Bandit Feedback

Policy optimization methods are one of the most widely used classes of R...
02/19/2020 ∙ by Yonathan Efroni, et al. ∙ 0 ∙ share

read it
Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning

Multi-step greedy policies have been extensively used in model-based Rei...
10/07/2019 ∙ by Manan Tomar, et al. ∙ 0 ∙ share

read it
Multi-Step Greedy and Approximate Real Time Dynamic Programming

Real Time Dynamic Programming (RTDP) is a well-known Dynamic Programming...
09/10/2019 ∙ by Yonathan Efroni, et al. ∙ 0 ∙ share

read it
Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs

Trust region policy optimization (TRPO) is a popular and empirically suc...
09/06/2019 ∙ by Lior Shani, et al. ∙ 0 ∙ share

read it
Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

State-of-the-art efficient model-based Reinforcement Learning (RL) algor...
05/27/2019 ∙ by Yonathan Efroni, et al. ∙ 0 ∙ share

read it
Action Robust Reinforcement Learning and Applications in Continuous Control

A policy is said to be robust if it maximizes the reward while consideri...
01/26/2019 ∙ by Chen Tessler, et al. ∙ 0 ∙ share

read it
Revisiting Exploration-Conscious Reinforcement Learning

The objective of Reinforcement Learning is to learn an optimal policy by...
12/13/2018 ∙ by Lior Shani, et al. ∙ 0 ∙ share

read it
How to Combine Tree-Search Methods in Reinforcement Learning

Finite-horizon lookahead policies are abundantly used in Reinforcement L...
09/06/2018 ∙ by Yonathan Efroni, et al. ∙ 0 ∙ share

read it
Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning

Multiple-step lookahead policies have demonstrated high empirical compet...
05/21/2018 ∙ by Yonathan Efroni, et al. ∙ 0 ∙ share

read it
Beyond the One Step Greedy Approach in Reinforcement Learning

The famous Policy Iteration algorithm alternates between policy improvem...
02/10/2018 ∙ by Yonathan Efroni, et al. ∙ 0 ∙ share

read it

Yonathan Efroni

Featured Co-authors

Shie Mannor

Mohammad Ghavamzadeh

Matteo Pirotta

Uri Shalit

Bruno Scherrer

Gal Dalal

Chen Tessler

Guy Tennenholtz

Nadav Merlis

Aviv Rosenberg

Lior Shani

Reinforcement Learning with Trajectory Feedback

Bandits with Partially Observable Offline Data

Mirror Descent Policy Optimization

Exploration-Exploitation in Constrained MDPs

Optimistic Policy Optimization with Bandit Feedback

Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning

Multi-Step Greedy and Approximate Real Time Dynamic Programming

Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs

Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

Action Robust Reinforcement Learning and Applications in Continuous Control

Revisiting Exploration-Conscious Reinforcement Learning

How to Combine Tree-Search Methods in Reinforcement Learning

Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning

Beyond the One Step Greedy Approach in Reinforcement Learning