IEEE

Deep Reinforcement Learning-Driven Dynamic Spectrum Access in Dense Wi-Fi Environments

Abstract: The rapid growth of wireless devices and bandwidth-intensive applications in urban environments has exacerbated spectrum congestion in Wi-Fi networks, resulting in performance degradation in ...
IEEE

DRL-ABS: Deep Reinforcement Learning-Based Adaptive Buffer Sizing for Edge Routers in AIoT Networks

Abstract: The proliferation of edge Internet of Things (IoT) devices intensifies congestion challenges in edge IoT networks. Adjusting edge router buffer sizes is a common and effective solution to ...
GitHub

DSRL for π₀: Diffusion Steering via Reinforcement Learning

This repository provides the official implementation for our paper: Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025). Specifically, it contains a JAX-based ...
GitHub

SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts

[2025-09-28] 🎉 SPEC-RL Release! Official release of SPEC-RL with 2–3× rollout acceleration and seamless integration into PPO, GRPO, and DAPO workflows.
Digi Times

Google reportedly launches TorchTPU project to boost TPU compatibility with PyTorch

Google has reportedly initiated the TorchTPU project to enhance support for the PyTorch machine learning framework on its tensor processing units (TPUs), aiming to challenge the software dominance of ...
Reuters

Exclusive: Google works to erode Nvidia's software advantage with Meta's help

Google's TorchTPU aims to enhance TPU compatibility with PyTorch Google seeks to help AI developers reduce reliance on Nvidia's CUDA ecosystem TorchTPU initiative is part of Google's plan to attract ...