Featured

Interoceptive Attention: a Finite-Bandwidth Mechanism for Homeostatic Prioritisation
Latest

Interoceptive Attention: a Finite-Bandwidth Mechanism for Homeostatic Prioritisation

An agent with a finite perceptual bandwidth and four competing bodily needs decides where to spend its precision. Selective allocation more than doubles survival; reversing the direction makes it worse than uniform. A web walkthrough of Paper 1 (SAB 2026).

St John · 18 May 2026
  1. A Taste of Reinforcement Learning

    A Taste of Reinforcement Learning

    St John · 20 Apr 2026
  2. Predicting Protein Function with DeepChain

    Predicting Protein Function with DeepChain

    St John · 12 May 2021
  3. A Productive Study and Research Workflow with Notion

    A Productive Study and Research Workflow with Notion

    St John · 18 Apr 2021
  4. Causal Reinforcement Learning: A Primer

    Causal Reinforcement Learning: A Primer

    St John · 9 Dec 2020
  5. World Models: Learning by Imagination

    World Models: Learning by Imagination

    St John · 28 May 2020
  6. Learning with a Policy

    Learning with a Policy

    St John · 25 May 2020

Latest

The Problem of Fairness. 1 Feb 2023 Differential Equations vs. Structural Causal Models. Differential Equations vs. Structural Causal Models. 10 Sept 2022 On Banking, Points & Rewards On Banking, Points & Rewards 1 Feb 2022 So Many Options! So Many Options! 17 Apr 2021 CRL Task 6: Causal Imitation Learning CRL Task 6: Causal Imitation Learning 16 Jan 2021 Causal RL Wrapping Up: Where to? Causal RL Wrapping Up: Where to? 16 Jan 2021 CRL Task 4: Generalisability and Robustness CRL Task 4: Generalisability and Robustness 15 Jan 2021 CRL Task 5: Learning Causal Models CRL Task 5: Learning Causal Models 15 Jan 2021 CRL Task 3: Counterfactual Decision Making CRL Task 3: Counterfactual Decision Making 17 Dec 2020