Asking Why.A place to share all the interesting things I find along the way.https://stjohngrimbly.com/en-GBInteroceptive Attention: a Finite-Bandwidth Mechanism for Homeostatic Prioritisationhttps://stjohngrimbly.com/interoceptive-attention/https://stjohngrimbly.com/interoceptive-attention/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).Mon, 18 May 2026 00:00:00 GMTactive-inferenceattentionhomeostasisinteroceptionA Taste of Reinforcement Learninghttps://stjohngrimbly.com/a-taste-of-reinforcement-learning/https://stjohngrimbly.com/a-taste-of-reinforcement-learning/A hands-on introduction to reinforcement learning — from the MDP framework and Bellman equation to Q-learning and beyond, with an interactive gridworld demo.Mon, 20 Apr 2026 00:00:00 GMTreinforcement-learningtutorialThe Problem of Fairness.https://stjohngrimbly.com/the-problem-of-fairness/https://stjohngrimbly.com/the-problem-of-fairness/In an causally unfair world, can we be selective?Wed, 01 Feb 2023 00:00:00 GMTcausalityfairnessDifferential Equations vs. Structural Causal Models.https://stjohngrimbly.com/DEs-SCMs/https://stjohngrimbly.com/DEs-SCMs/On the relationship between differential equations and causal modelling.Sat, 10 Sep 2022 00:00:00 GMTcausalityOn Banking, Points & Rewardshttps://stjohngrimbly.com/credit-cards/https://stjohngrimbly.com/credit-cards/Abuse those credit cards.Tue, 01 Feb 2022 00:00:00 GMTfinancePredicting Protein Function with DeepChainhttps://stjohngrimbly.com/protein-function/https://stjohngrimbly.com/protein-function/A walkthrough of how I created a DeepChain app for predicting Gene Ontology given only a protein sequence.Wed, 12 May 2021 00:00:00 GMTmachine-learningbiologyA Productive Study and Research Workflow with Notionhttps://stjohngrimbly.com/notion-setup/https://stjohngrimbly.com/notion-setup/A guide on how to set up the ultimate research workflow with Notion.Sun, 18 Apr 2021 00:00:00 GMTproductivitytutorialSo Many Options!https://stjohngrimbly.com/so-many-option/https://stjohngrimbly.com/so-many-option/On the Black-Scholes Method for Options Valuation.Sat, 17 Apr 2021 00:00:00 GMTfinancetutorialcodeCRL Task 6: Causal Imitation Learninghttps://stjohngrimbly.com/causal-imitation/https://stjohngrimbly.com/causal-imitation/Sat, 16 Jan 2021 00:00:00 GMTcausalityreinforcement-learningmachine-learningCausal RL Wrapping Up: Where to?https://stjohngrimbly.com/wrapping-up/https://stjohngrimbly.com/wrapping-up/Sat, 16 Jan 2021 00:00:00 GMTcausalityreinforcement-learningCRL Task 4: Generalisability and Robustnesshttps://stjohngrimbly.com/generalise/https://stjohngrimbly.com/generalise/Fri, 15 Jan 2021 00:00:00 GMTcausalityreinforcement-learningmachine-learningCRL Task 5: Learning Causal Modelshttps://stjohngrimbly.com/learning-models/https://stjohngrimbly.com/learning-models/Fri, 15 Jan 2021 00:00:00 GMTcausalityreinforcement-learningmachine-learningCRL Task 3: Counterfactual Decision Makinghttps://stjohngrimbly.com/counterfactual/https://stjohngrimbly.com/counterfactual/Thu, 17 Dec 2020 00:00:00 GMTcausalityreinforcement-learningCRL Task 2: Interventions - When and Where?https://stjohngrimbly.com/interventions/https://stjohngrimbly.com/interventions/Wed, 16 Dec 2020 00:00:00 GMTcausalityreinforcement-learningCRL Task 1: Generalised Policy Learninghttps://stjohngrimbly.com/generalised-PL/https://stjohngrimbly.com/generalised-PL/Mon, 14 Dec 2020 00:00:00 GMTcausalityreinforcement-learningPreliminaries for CRLhttps://stjohngrimbly.com/CRL-preliminaries/https://stjohngrimbly.com/CRL-preliminaries/Thu, 10 Dec 2020 00:00:00 GMTcausalityreinforcement-learningmachine-learningCausal Reinforcement Learning: A Primerhttps://stjohngrimbly.com/causal-reinforcement-learning/https://stjohngrimbly.com/causal-reinforcement-learning/Wed, 09 Dec 2020 00:00:00 GMTcausalityreinforcement-learningmachine-learningThe Do-Calculushttps://stjohngrimbly.com/the-do-calculus/https://stjohngrimbly.com/the-do-calculus/Thu, 10 Sep 2020 00:00:00 GMTcausalityFaithfulnesshttps://stjohngrimbly.com/faithfulness/https://stjohngrimbly.com/faithfulness/Mon, 07 Sep 2020 00:00:00 GMTcausalityReaching Rung 3: Counterfactual Reasoninghttps://stjohngrimbly.com/reaching-rung-3/https://stjohngrimbly.com/reaching-rung-3/Sun, 06 Sep 2020 00:00:00 GMTcausalityInterventions and Multivariate SCMshttps://stjohngrimbly.com/multivariate-SCMs/https://stjohngrimbly.com/multivariate-SCMs/Tue, 01 Sep 2020 00:00:00 GMTcausalitymachine-learningCausality and Machine Learninghttps://stjohngrimbly.com/causality-and-machine-learning/https://stjohngrimbly.com/causality-and-machine-learning/How causality ties into machine learning and analytics.Mon, 10 Aug 2020 00:00:00 GMTcausalitymachine-learningLearning Causal Modelshttps://stjohngrimbly.com/learning-causal-models/https://stjohngrimbly.com/learning-causal-models/Learning structural causal models from data.Sun, 09 Aug 2020 00:00:00 GMTcausalitymachine-learningCausal Modelshttps://stjohngrimbly.com/Causal-Models/https://stjohngrimbly.com/Causal-Models/Introduction to structural causal models.Fri, 07 Aug 2020 00:00:00 GMTcausalityA Causal Perspectivehttps://stjohngrimbly.com/a-causal-perspective/https://stjohngrimbly.com/a-causal-perspective/A Causal Perspective.Wed, 05 Aug 2020 00:00:00 GMTcausalityUncertainty in Model Based RLhttps://stjohngrimbly.com/uncertainty-in-MBRL/https://stjohngrimbly.com/uncertainty-in-MBRL/Uncertainty in Model Based RL.Sat, 13 Jun 2020 00:00:00 GMTreinforcement-learningmachine-learningExploration vs Exploitationhttps://stjohngrimbly.com/exploration-vs-exploitation/https://stjohngrimbly.com/exploration-vs-exploitation/Exploration vs Exploitation.Wed, 10 Jun 2020 00:00:00 GMTreinforcement-learningneuroscienceFree Energy of Expected Futurehttps://stjohngrimbly.com/free-energy-of-expected-future/https://stjohngrimbly.com/free-energy-of-expected-future/Free energy of expected future.Mon, 08 Jun 2020 00:00:00 GMTreinforcement-learningneuroscienceIntroduction to Reinforcement Learninghttps://stjohngrimbly.com/intro-to-RL/https://stjohngrimbly.com/intro-to-RL/An introduction to deep reinforcement learning.Sun, 07 Jun 2020 00:00:00 GMTreinforcement-learningtutorialLearning with a Modelhttps://stjohngrimbly.com/model-based-RL/https://stjohngrimbly.com/model-based-RL/An introduction to model-free reinforcement learning.Thu, 04 Jun 2020 00:00:00 GMTreinforcement-learningmachine-learningcodeWorld Models: Learning by Imaginationhttps://stjohngrimbly.com/world-models/https://stjohngrimbly.com/world-models/An overview of the world models paper.Thu, 28 May 2020 00:00:00 GMTreinforcement-learningmachine-learningThe Mathematics of Predictive Processinghttps://stjohngrimbly.com/intro-to-predictive-processing/https://stjohngrimbly.com/intro-to-predictive-processing/Hello! Today we'll be discussing the mathematics of predictive processing - a modern theory for how much of the processing of information is done in the brain. This is also an active area of research with an impact on research…Mon, 25 May 2020 00:00:00 GMTneurosciencetutorialLearning with a Policyhttps://stjohngrimbly.com/model-free-RL/https://stjohngrimbly.com/model-free-RL/Model-Free RL: Policy Methods.Mon, 25 May 2020 00:00:00 GMTreinforcement-learningmachine-learningcode