Tech Xplore

Why reinforcement learning breaks at scale, and how a new method fixes it

From autonomous cars to video games, reinforcement learning (machine learning through interaction with environments) can have ...
IEEE

A Deep Reinforcement Learning Approach for Synchronization Between Two Memristor Chaotic Systems and Application for Image Encryption

Abstract: This study proposes a novel synchronization framework for memristive chaotic systems (MCSs) through an enhanced deep reinforcement learning (DRL) approach, featuring an improved proximal ...
AZoRobotics on MSN

Simulation-only training enables quadruped robots to master real-world terrain

A quadruped robot uses deep reinforcement learning to master walking on varied terrains, demonstrating energy-efficient and adaptive locomotion in simulation.
Frontiers

Latency and trust constrained fog node selection using deep reinforcement learning

Automated healthcare IoT systems demand secure, low-latency, and energy-efficient computation—capabilities well-supported by fog computing. Effective selection of fog nodes is critical for maximizing ...
Frontiers

LG-H-PPO: offline hierarchical PPO for robot path planning on a latent graph

The path planning capability of autonomous robots in complex environments is crucial for their widespread application in the real world. However, long-term decision-making and sparse reward signals ...
blockchain

DeepMind Unveils AI System That Discovers Novel Reinforcement Learning Algorithms, Surpassing Human Designs

According to God of Prompt on Twitter, DeepMind has published groundbreaking research in Nature led by David Silver, introducing an AI meta-learning system capable of autonomously discovering entirely ...
blockchain

List of AI News about reinforcement learning algorithms

According to God of Prompt on Twitter, DeepMind has published groundbreaking research in Nature led by David Silver, introducing an AI meta-learning system capable of autonomously discovering entirely ...
marktechpost

Weak-for-Strong (W4S): A Novel Reinforcement Learning Algorithm that Trains a weak Meta Agent to Design Agentic Workflows with Stronger LLMs

W4S operates in turns. The state contains task instructions, the current workflow program, and feedback from prior executions. An action has 2 components, an analysis of what to change, and new Python ...
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.