Plasticity as the Mirror of Empowerment (David Abel) - Sensorimotor AI Journal Club
Two weeks ago, David Abel argued that RL’s central concepts need precise mathematical definitions. Last week, Mani Hamidi responded through the lens of evolutionary theory, focusing in particular on adaptation. Both talks emphasized one gap: we talk about agents constantly, but we still lack a formal vocabulary for their properties, the way physics has mass and energy for inanimate matter.
Two weeks ago, David Abel argued that RL’s central concepts need precise mathematical definitions. Last week, Mani Hamidi responded through the lens of evolutionary theory, focusing in particular on adaptation . Both talks emphasized one gap: we talk about agents constantly, but we still lack a formal vocabulary for their properties, the way physics has mass and energy for inanimate matter. Today, Dave returned with a concrete proposal: plasticity and empowerment might be the elemental properties of agents. He formalized both using a single information-theoretic tool, showed they are exact mir
saved by
related reading
- Illuminating the Three Dogmas of RL under Evolutionary Light (Mani Hamidi) - Sensorimotor AI Journal Clubsensorimotorai.github.io
- [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
- The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Evolution as Backstop for Reinforcement Learning · Gwern.netgwern.net
- Embedded Agency (full-text version) — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agencymindthefuture.info
- OpenAI researcher on agent swarms & recursive self-improvementyoutube.com
- How Can Interpretability Researchers Help AGI Go Well? — AI Alignment Forumalignmentforum.org
- Questions about the Future of AI - by Dwarkesh Pateldwarkesh.com
- Open-minded updatelessness — LessWronglesswrong.com
- [1703.04908] Emergence of Grounded Compositional Language in Multi-Agent Populationsarxiv.org