LESSWRONG
is fundraising!
Tags
LW
$

Reinforcement Learning

•

Applied to RL, but don't do anything I wouldn't do by Gunnar_Zarncke 14d ago

•

Applied to Automated monitoring systems by hiki_t 23d ago

•

Applied to Why Recursive Self-Improvement Might Not Be the Existential Risk We Fear by Nassim_A 1mo ago

•

Applied to Reinforcement Learning: Essential Step Towards AGI or Irrelevant? by Double 2mo ago

•

Applied to The Explore vs. Exploit Dilemma by nathanjzhao 2mo ago

•

Applied to On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback by Marcus Williams 2mo ago

•

Applied to [Paper] Hidden in Plain Text: Emergence and Mitigation of Steganographic Collusion in LLMs by Yohan Mathew 3mo ago

•

Applied to Inference-Only Debate Experiments Using Math Problems by Arjun Panickssery 5mo ago

•

Applied to Pacing Outside the Box: RNNs Learn to Plan in Sokoban by Adrià Garriga-alonso 5mo ago

•

Applied to On predictability, chaos and AIs that don't game our goals by Alejandro Tlaie 5mo ago

•

Applied to Towards shutdownable agents via stochastic choice by EJT 5mo ago

•

Applied to (Appetitive, Consummatory) ≈ (RL, reflex) by Steven Byrnes 6mo ago

•

Applied to Language for Goal Misgeneralization: Some Formalisms from my MSc Thesis by Giulio 6mo ago

•

Applied to The Carnot Engine of Economics by StrivingForLegibility 7mo ago

•

Applied to Finding the estimate of the value of a state in RL agents by Clément Dumas 8mo ago

•

Applied to Speedrun ruiner research idea by lemonhope 8mo ago