Picture for Pihe Hu

Pihe Hu

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training

Add code
Sep 28, 2024
Viaarxiv icon

Mixed Sparsity Training: Achieving 4$\times$ FLOP Reduction for Transformer Pretraining

Add code
Aug 21, 2024
Viaarxiv icon

Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation

Add code
Jul 06, 2023
Viaarxiv icon

Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning

Add code
Aug 30, 2022
Figure 1 for Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning
Figure 2 for Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning
Figure 3 for Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning
Figure 4 for Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning
Viaarxiv icon

Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation

Add code
Jun 23, 2022
Figure 1 for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Figure 2 for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Figure 3 for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Viaarxiv icon

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

Add code
May 30, 2022
Figure 1 for RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
Figure 2 for RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
Figure 3 for RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
Figure 4 for RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
Viaarxiv icon