Picture for Jun Jet Tai

Jun Jet Tai

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

Add code
Oct 13, 2024
Viaarxiv icon

Gymnasium: A Standard Interface for Reinforcement Learning Environments

Add code
Jul 24, 2024
Viaarxiv icon

PyFlyt -- UAV Simulation Environments for Reinforcement Learning Research

Add code
Apr 03, 2023
Viaarxiv icon

Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics

Add code
Aug 22, 2022
Figure 1 for Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics
Figure 2 for Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics
Figure 3 for Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics
Figure 4 for Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics
Viaarxiv icon

FasteNet: A Fast Railway Fastener Detector

Add code
Dec 14, 2020
Figure 1 for FasteNet: A Fast Railway Fastener Detector
Figure 2 for FasteNet: A Fast Railway Fastener Detector
Figure 3 for FasteNet: A Fast Railway Fastener Detector
Figure 4 for FasteNet: A Fast Railway Fastener Detector
Viaarxiv icon

BOBBY2: Buffer Based Robust High-Speed Object Tracking

Add code
Oct 18, 2019
Figure 1 for BOBBY2: Buffer Based Robust High-Speed Object Tracking
Figure 2 for BOBBY2: Buffer Based Robust High-Speed Object Tracking
Figure 3 for BOBBY2: Buffer Based Robust High-Speed Object Tracking
Figure 4 for BOBBY2: Buffer Based Robust High-Speed Object Tracking
Viaarxiv icon