Picture for Jonathan Lee

Jonathan Lee

Mesoscale Traffic Forecasting for Real-Time Bottleneck and Shockwave Prediction

Add code
Feb 08, 2024
Figure 1 for Mesoscale Traffic Forecasting for Real-Time Bottleneck and Shockwave Prediction
Figure 2 for Mesoscale Traffic Forecasting for Real-Time Bottleneck and Shockwave Prediction
Figure 3 for Mesoscale Traffic Forecasting for Real-Time Bottleneck and Shockwave Prediction
Figure 4 for Mesoscale Traffic Forecasting for Real-Time Bottleneck and Shockwave Prediction
Viaarxiv icon

Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models

Add code
Aug 30, 2023
Figure 1 for Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Figure 2 for Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Figure 3 for Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Figure 4 for Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Viaarxiv icon

Dueling RL: Reinforcement Learning with Trajectory Preferences

Add code
Nov 08, 2021
Viaarxiv icon

Design of Experiments for Stochastic Contextual Linear Bandits

Add code
Jul 22, 2021
Figure 1 for Design of Experiments for Stochastic Contextual Linear Bandits
Figure 2 for Design of Experiments for Stochastic Contextual Linear Bandits
Figure 3 for Design of Experiments for Stochastic Contextual Linear Bandits
Figure 4 for Design of Experiments for Stochastic Contextual Linear Bandits
Viaarxiv icon

Near Optimal Policy Optimization via REPS

Add code
Mar 17, 2021
Viaarxiv icon

Is Q-Learning Provably Efficient? An Extended Analysis

Add code
Sep 22, 2020
Figure 1 for Is Q-Learning Provably Efficient? An Extended Analysis
Figure 2 for Is Q-Learning Provably Efficient? An Extended Analysis
Figure 3 for Is Q-Learning Provably Efficient? An Extended Analysis
Viaarxiv icon

Continuous Online Learning and New Insights to Online Imitation Learning

Add code
Dec 03, 2019
Viaarxiv icon

On-Policy Robot Imitation Learning from a Converging Supervisor

Add code
Jul 08, 2019
Figure 1 for On-Policy Robot Imitation Learning from a Converging Supervisor
Figure 2 for On-Policy Robot Imitation Learning from a Converging Supervisor
Figure 3 for On-Policy Robot Imitation Learning from a Converging Supervisor
Viaarxiv icon

Online Learning with Continuous Variations: Dynamic Regret and Reductions

Add code
Feb 19, 2019
Viaarxiv icon

Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models

Add code
Nov 19, 2018
Figure 1 for Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models
Figure 2 for Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models
Figure 3 for Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models
Figure 4 for Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models
Viaarxiv icon