Alert button
Picture for Ofir Nachum

Ofir Nachum

Alert button

Contrastive Value Learning: Implicit Models for Simple Offline RL

Nov 03, 2022
Bogdan Mazoure, Benjamin Eysenbach, Ofir Nachum, Jonathan Tompson

Figure 1 for Contrastive Value Learning: Implicit Models for Simple Offline RL
Figure 2 for Contrastive Value Learning: Implicit Models for Simple Offline RL
Figure 3 for Contrastive Value Learning: Implicit Models for Simple Offline RL
Figure 4 for Contrastive Value Learning: Implicit Models for Simple Offline RL
Viaarxiv icon

Oracle Inequalities for Model Selection in Offline Reinforcement Learning

Nov 03, 2022
Jonathan N. Lee, George Tucker, Ofir Nachum, Bo Dai, Emma Brunskill

Figure 1 for Oracle Inequalities for Model Selection in Offline Reinforcement Learning
Viaarxiv icon

Dichotomy of Control: Separating What You Can Control from What You Cannot

Oct 24, 2022
Mengjiao Yang, Dale Schuurmans, Pieter Abbeel, Ofir Nachum

Figure 1 for Dichotomy of Control: Separating What You Can Control from What You Cannot
Figure 2 for Dichotomy of Control: Separating What You Can Control from What You Cannot
Figure 3 for Dichotomy of Control: Separating What You Can Control from What You Cannot
Figure 4 for Dichotomy of Control: Separating What You Can Control from What You Cannot
Viaarxiv icon

Understanding HTML with Large Language Models

Oct 08, 2022
Izzeddin Gur, Ofir Nachum, Yingjie Miao, Mustafa Safdari, Austin Huang, Aakanksha Chowdhery, Sharan Narang, Noah Fiedel, Aleksandra Faust

Figure 1 for Understanding HTML with Large Language Models
Figure 2 for Understanding HTML with Large Language Models
Figure 3 for Understanding HTML with Large Language Models
Figure 4 for Understanding HTML with Large Language Models
Viaarxiv icon

PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations

Jul 27, 2022
Kuang-Huei Lee, Ofir Nachum, Tingnan Zhang, Sergio Guadarrama, Jie Tan, Wenhao Yu

Figure 1 for PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
Figure 2 for PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
Figure 3 for PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
Figure 4 for PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
Viaarxiv icon

Joint Representation Training in Sequential Tasks with Shared Structure

Jun 24, 2022
Aldo Pacchiano, Ofir Nachum, Nilseh Tripuraneni, Peter Bartlett

Viaarxiv icon

A Mixture-of-Expert Approach to RL-based Dialogue Management

May 31, 2022
Yinlam Chow, Aza Tulepbergenov, Ofir Nachum, MoonKyung Ryu, Mohammad Ghavamzadeh, Craig Boutilier

Figure 1 for A Mixture-of-Expert Approach to RL-based Dialogue Management
Figure 2 for A Mixture-of-Expert Approach to RL-based Dialogue Management
Figure 3 for A Mixture-of-Expert Approach to RL-based Dialogue Management
Figure 4 for A Mixture-of-Expert Approach to RL-based Dialogue Management
Viaarxiv icon

Multi-Game Decision Transformers

May 30, 2022
Kuang-Huei Lee, Ofir Nachum, Mengjiao Yang, Lisa Lee, Daniel Freeman, Winnie Xu, Sergio Guadarrama, Ian Fischer, Eric Jang, Henryk Michalewski, Igor Mordatch

Figure 1 for Multi-Game Decision Transformers
Figure 2 for Multi-Game Decision Transformers
Figure 3 for Multi-Game Decision Transformers
Figure 4 for Multi-Game Decision Transformers
Viaarxiv icon

Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters

May 27, 2022
Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu, Ofir Nachum

Figure 1 for Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters
Figure 2 for Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters
Figure 3 for Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters
Figure 4 for Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters
Viaarxiv icon

Chain of Thought Imitation with Procedure Cloning

May 22, 2022
Mengjiao Yang, Dale Schuurmans, Pieter Abbeel, Ofir Nachum

Figure 1 for Chain of Thought Imitation with Procedure Cloning
Figure 2 for Chain of Thought Imitation with Procedure Cloning
Figure 3 for Chain of Thought Imitation with Procedure Cloning
Figure 4 for Chain of Thought Imitation with Procedure Cloning
Viaarxiv icon