Lina Tlemcani·Jan 12Soft Actor Critic in RL: Gold Standard for Milano2026 Paralympic RoboticsIf you’ve spent any time training agents in continuous action spaces — like robotic arms or bipedal walkers — you’ve likely encountered…A response icon1A response icon1
Caroline Terryn·Jan 12Soft-Actor Critic Explanation and Performance on the Cart-Pole Balance TaskIntroduction to SAC as an RL Algorithm
Gaus Mohiuddin Sayyad·Jan 12Evaluating a Universal Soft Actor-Critic Controller for Multi-Functional Assistive Robotics : SAC…This project evaluates whether a single, universal Soft Actor-Critic (SAC) implementation can robustly learn multiple distinct assistive…A response icon4A response icon4
BalvinderDhillon·Jan 11The Virtual Patient: Using Reinforcement Learning to Rethink Brain Tumour TreatmentsEvery day in the United Kingdom, about 10 people are diagnosed with glioblastoma, the most aggressive form of brain cancer (3,600 new cases…A response icon2A response icon2
Junkai Wang·Jan 11Soft Actor-Critic (SAC) for Continuous Control: An Introduction and Possible Implications for…This tutorial (Actually my coursework) assumes that the reader has a basic understanding of reinforcement learning concepts such as states…A response icon5A response icon5
Ashritha·Jan 11Soft Actor-Critic for Robust Control under Monte Carlo Sampled DynamicsLearning stable policies when the environment won’t sit still
Edward Goh·Jan 11Soft Actor–Critic for Insulin Dosing: A Maximum-Entropy Reinforcement Learning Approach to Glucose…Soft Actor-Critic (SAC) is a popular reinforcement learning algorithm for continuous control problems, known for being both stable and…
Tauheed Ibrahim·Jan 9Soft Actor–Critic Overview: Through the Lens of Closed-Loop NeuromodulationSoft actor-critic (SAC) is an off-policy reinforcement learning algorithm that combines reward maximisation with entropy regularisation.A response icon1A response icon1
ZihuiChen·Dec 31, 2025Soft Actor-Critic (SAC) for Prosthetic-Like Control Under DriftA practical Soft Actor-Critic (SAC) tutorial: maximum-entropy off-policy control with motor bias/weakness faults and rehabilitation-style…A response icon1A response icon1
