Agents that act from beliefs
Designing controllers that infer hidden state, evaluate possible futures and act while tracking uncertainty, rather than simply mapping observations to actions.
Consulting, advisory and research collaboration
Uncertainty-aware world models for physical AI, robotics and adaptive decision-making.
I build and advise on systems that maintain beliefs about hidden states, act under uncertainty and recover when observations do not fit predictions. The work combines active inference, generative models, dynamical systems and neurocomputational modelling.
Active inference
World models
Embodied AI
Robotics
Bayesian inference
Adaptive decision systems
What this is
A practical route from neuroscience-inspired theory to inspectable AI systems.
I am especially interested in systems where behaviour depends on incomplete evidence: robots in cluttered spaces, autonomous agents that need to search and revise beliefs, decision systems with changing context and scientific data where the hidden causes matter more than surface prediction.
Internal models that can be inspected
Building small but explicit generative models of objects, scenes, observations, policies and failures, so behaviour can be debugged mechanistically.
Planning beyond a fixed reward
Using active inference and expected-free-energy-style objectives to balance goal pursuit, safety, information gain, stability and changing context.
Portfolio
Selected demos and research prototypes.
Across these demos, the theme is the same: agents acting under uncertainty, using generative models, semantic priors and belief updating to move from perception to action in games, gridworlds, drones, robots and embodied world-model simulations.
Drone control
View demo and write-up →
Polyphonic active inference drone
A 3D PyBullet drone controller with noisy self-observations, egocentric target cues, ray-based obstacle sensing, belief-state control and scene-aware policy evaluation.
World model
Open world model lab →
House-search semantic world model
An embodied agent searches for a cup using semantic priors, planned inspection, negative evidence, belief updating and route redirection.
Embodied AI
View robot page →
Active inference robot
A 3D physics example where perception, action, correction and recovery are tied together through a generative model and active inference loop.
Multi-objective control
View gridworld write-up →
Polyphonic gridworld
A partially observed gridworld where safety, goal pursuit, energy maintenance, uncertainty reduction and habit are kept explicit and negotiated online.
Real-time inference
Open Pong demo →
Thermodynamic VL Pong agent
A compact real-time example of posterior updating and action selection through a lightweight thermodynamic variational Laplace scheme.
Research programme
Read the public record →
Coordination without command
A broader research direction on how coherent behaviour can emerge without a single central controller, linking active inference, robotics and adaptive intelligence.
Why it matters
The point is not just another agent demo.
Many AI systems behave impressively until the world changes, evidence becomes partial, or the task requires them to know when they do not know. My interest is in agents and decision systems with explicit internal state: what they believe, what they expect, what they are uncertain about and why a particular action was chosen.
Consulting and advisory
Clear ways to work together.
Best fit: early-stage R&D, technical strategy, prototype design, feasibility assessment, academic-industry bids, or teams who need a principled modelling view before committing to a larger build.
Scoping / feasibility
A focused review of whether active inference, world models or uncertainty-aware control are relevant to your problem.
£500-£1,200
- 1-2 hour call
- Technical summary note
- Prototype route and risk assessment
Prototype sprint
A small but concrete demo, model, simulation, dashboard or analysis pipeline that makes the idea inspectable.
£2k-£10k+
- Defined milestone and deliverable
- Simulation or modelling prototype
- Code, figures and written explanation
Advisory / retainer
Ongoing scientific and technical input for AI, robotics, neurotechnology, modelling or decision-system projects.
£1.5k-£5k / month
- Regular advisory calls
- Technical review and architecture input
- Support for papers, bids or product strategy
Also open to
Invited talks, academic collaborations, grant consortia, fractional advisory roles, industry fellowships and selective consulting around active inference, world models, embodied AI and mechanistic modelling.
Not a software house
The strongest fit is where the problem is conceptually hard and a principled model, prototype or technical review is more valuable than just building a polished interface.
Contact
Bring a hard problem, a possible collaboration, or a half-formed idea.
I lead the Computational Psychiatry & Neuropharmacological Systems (CPNS) Lab. For consulting, advisory work, speaking or research partnerships, email me with a short description of the problem and what kind of help would be useful.
Suggested subject line: Consulting / world models enquiry