The Lancet

Development and validation of a machine-learning model to reduce futile procurements in donations after circulatory death in liver transplantation in the USA…

We show that, compared with surgeon predictions and existing risk-prediction tools, our machine-learning model can enhance ...
IEEE

Interpretable Multi-Agent Reinforcement Learning for Traffic Signal Control: Influence Mechanism and Piecewise Linear Approximation

Abstract: Traffic signal control plays a crucial role in intelligent transportation systems, with cooperative control being challenging to implement but essential for its effectiveness. Many methods ...
IEEE

MetaSignal: Meta Reinforcement Learning for Traffic Signal Control via Fourier Basis Approximation

Abstract: Traffic signal control plans significantly impact transportation system efficiency by regulating traffic conditions at intersections. Adaptive traffic plans that can adjust to real-time road ...
GitHub

Boosting Efficient Reinforcement Learning for Vision-and-Language Navigation With Open-Sourced LLM

This repository is the official implementation of Boosting Efficient Reinforcement Learning for Vision-and-Language Navigation With Open-Sourced LLM. We opt for a simple reward function for two main ...
Machine Design

eBook: Efficient Linear Motion Design with Smart Bearing Selection

Unlock the keys to designing high-performance linear motion systems with expert insights on bearings, drive technologies, and precision engineering. This e-book is a comprehensive guide to designing ...
marktechpost

Polaris-4B and Polaris-7B: Post-Training Reinforcement Learning for Efficient Math and Logic Reasoning

Advanced reasoning models are at the frontier of machine intelligence, especially in domains like math problem-solving and symbolic reasoning. These models are designed to perform multi-step ...
Science Daily

The brain’s sweet spot: How criticality could unlock learning, memory—and prevent Alzheimer’s

Our brains may work best when teetering on the edge of chaos. A new theory suggests that criticality a sweet spot between order and randomness is the secret to learning, memory, and adaptability. When ...
Scientific Research Publishing

Nguyen-Tang, T., Yin, M., Gupta, S., Venkatesh, S. and Arora, R. (2023) On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation ...

ABSTRACT: Offline reinforcement learning (RL) focuses on learning policies using static datasets without further exploration. With the introduction of distributional reinforcement learning into ...
GitHub

An efficient method of spline approximation for power function

Let $P(m, X, N)$ be an $m$-degree polynomial in $X\in\mathbb{R}$ having fixed non-negative integers $m$ and $N$. Essentially, the polynomial $P(m, X, N)$ is a result ...
marktechpost

Google DeepMind Achieves State-of-the-Art Data-Efficient Reinforcement Learning RL with Improved Transformer World Models

Reinforcement Learning RL trains agents to maximize rewards by interacting with an environment. Online RL alternates between taking actions, collecting observations and rewards, and updating policies ...
VentureBeat

DeepSeek-R1’s bold bet on reinforcement learning: How it outpaced OpenAI at 3% of the cost

DeepSeek-R1's release last Monday has sent shockwaves through the AI community, disrupting assumptions about what’s required to achieve cutting-edge AI performance. Matching OpenAI’s o1 at just 3%-5% ...