Reinforcement Learning's Safety Dance: Balancing Risk and Reward
Reinforcement learning meets model predictive control to keep complex systems safe. But is this new approach the silver bullet it claims to be?
Read the full articleYou might also wanna read
Multi-Agent Reinforcement Learning Reduces Drone Racing Collisions by 50% While Achieving Champion-Level Performance
Champion-level multi-player drone racing with 50% fewer collisions via league-based self-play.
Understanding Reinforcement Learning for Model Training, and future directions with GRAPE
This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling,
arxiv.org·9mo ago
Reward-Channel Addiction: How Visible Incentives Can Break AI Safety Alignment
Deployed agents increasingly act with their reward proxy in view, such as a balance, score, or KPI dashboard. We show that reinforcement lea
arxiv.org·17d ago
Self-play reinforcement learning with minimal human data produces human-compatible autonomous driving policies
Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale
arxiv.org·19d agoSelf-play reinforcement learning with minimal human data produces human-compatible autonomous driving policies
Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale
arxiv.org·19d ago
DILLO: A Language-Based World Model for Proactive Agent Steering Without Visual Simulation
Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a para
arxiv.org·18d ago
AgentGym-RL: A Reinforcement Learning Framework for Training LLM Agents in Multi-Turn Decision Making
Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving f
arxiv.org·19d agoAgentGym-RL: A Reinforcement Learning Framework for Training LLM Agents in Multi-Turn Decision Making
Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving f
arxiv.org·19d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.