reinforcement learning

The Reassessment That Did Not Travel: What the 2020 Arcade Result About Exploration Bonuses Establishes, the Six Conditions That Made It Informative, and Which of Them the Language-Model Revival Drops

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Exploration bonuses have returned. Between 2025 and 2026 at least six frameworks added an intrinsic novelty or uncertainty term to reinforcement learning with verifiable rewards for language models, each naming a classical antecedent - prediction error, pseudo-coun...

Snorlax Control: Deep Reinforcement Learning with PPO and Pure-NumPy Inference

Experimental optimization and machine-learning prediction of sunn hemp fiber/fever nut shell particle hybrid epoxy composites

rslcpp - ROS Simulation Library for C++

rslcpp - the ROS simulation library for C++ - lets you turn a set of existing ROS 2 nodes into a deterministic simulation. Instead of the asynchronous, multi-process default execution of ROS 2, rslcpp aggregates all participating nodes in a single process and drives them through a custom executor under an explicit simu...

EEG: Probabilistic Selection and Depression

This dataset contains EEG recordings from 122 college-age participants performing a probabilistic selection task, collected circa 2008-2010 in the John J.B. Allen laboratory at the University of Arizona. Participants were selected based on reliably high or low scores on the Beck Depression Inventory, with some undergoi...

Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning

SkyNet: Belief-Aware Planning in Partially Observable Stochastic Games

Robust Regularized Policy Iteration Under Transition Uncertainty

THE LOGIC OF LEARNING MACHINES - How Artificial Intelligence Sees, Learns, Reasons, and Creates

The Logic of Learning Machines: How Artificial Intelligence Sees, Learns, Reasons, and Creates is a comprehensive educational textbook and reference work introducing the foundations, methods, applications, limitations, and future directions of artificial intelligence.Written for students and readers who want to progres...

Control-theoretic methods for reinforcement learning

Reinforcement Learning (RL) has become a cornerstone of modern artificial intelligence and control theory, enabling complex decision-making tasks in a wide variety of domains such as robotics, autonomous driving and strategic games. While deep neural networks allow RL methods to address large-scale problems, exploiting...

Motion Planning in Urban Environments via Self-Play Reinforcement Learning

International audience

AI-Assisted Self-Powered Flexible Electronic System for Energy Management

This review systematically examines recent progress in AI-enabled energy management strategies for self-powered flexible electronic systems and categorizes AI integration across three key dimensions: at the algorithmic level, predictive models and reinforcement learning enable dynamic power allocation and coordinate mu...