Picture for Wei Pan

Wei Pan

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning

Add code
Jun 01, 2024
Viaarxiv icon

TTA-Nav: Test-time Adaptive Reconstruction for Point-Goal Navigation under Visual Corruptions

Mar 14, 2024
Figure 1 for TTA-Nav: Test-time Adaptive Reconstruction for Point-Goal Navigation under Visual Corruptions
Figure 2 for TTA-Nav: Test-time Adaptive Reconstruction for Point-Goal Navigation under Visual Corruptions
Figure 3 for TTA-Nav: Test-time Adaptive Reconstruction for Point-Goal Navigation under Visual Corruptions
Figure 4 for TTA-Nav: Test-time Adaptive Reconstruction for Point-Goal Navigation under Visual Corruptions
Viaarxiv icon

Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control

Add code
Feb 27, 2024
Figure 1 for Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
Figure 2 for Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
Figure 3 for Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
Figure 4 for Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
Viaarxiv icon

Open Ad Hoc Teamwork with Cooperative Game Theory

Feb 23, 2024
Viaarxiv icon

Aligning Individual and Collective Objectives in Multi-Agent Cooperation

Add code
Feb 19, 2024
Viaarxiv icon

NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification

Dec 09, 2023
Figure 1 for NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification
Figure 2 for NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification
Figure 3 for NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification
Figure 4 for NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification
Viaarxiv icon

Language and Sketching: An LLM-driven Interactive Multimodal Multitask Robot Navigation Framework

Add code
Nov 14, 2023
Viaarxiv icon

Deep Bayesian Reinforcement Learning for Spacecraft Proximity Maneuvers and Docking

Nov 07, 2023
Viaarxiv icon

DACOOP-A: Decentralized Adaptive Cooperative Pursuit via Attention

Add code
Oct 28, 2023
Figure 1 for DACOOP-A: Decentralized Adaptive Cooperative Pursuit via Attention
Figure 2 for DACOOP-A: Decentralized Adaptive Cooperative Pursuit via Attention
Figure 3 for DACOOP-A: Decentralized Adaptive Cooperative Pursuit via Attention
Figure 4 for DACOOP-A: Decentralized Adaptive Cooperative Pursuit via Attention
Viaarxiv icon

Causal Discovery with Generalized Linear Models through Peeling Algorithms

Oct 25, 2023
Viaarxiv icon