04:00
2026-09-30
arxiv.org
machine-learning
Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden?
A new arXiv paper (2609.35897v1) presents the first causal mechanistic audit of a self-discovered reinforcement learning rule, Disco103, which previously surpassed PPO to reach state-of-the-art benchmβ¦