Manuel Baltieri
Research programme
Agents across fields
Selected work
Maths
Mathematical approaches to the study of agents
With Keisuke Suzuki, a review of mathematical approaches to studying agents across research fields.
Cognition
Disentangled representations for causal cognition
Relating causal representation learning to how natural and artificial agents acquire causal knowledge.
(A)Life
Hybrid Life: Integrating Biological, Artificial, and Cognitive Systems
A synthesis of biological, artificial, and cognitive perspectives on life and the formal languages that can connect them.
AI safety
Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
Work on compositional behavioural semantics and state abstraction in reinforcement learning.
Latest news (more)
Mathematical approaches to the study of agents
A unified review of mathematical approaches to individuality, normativity, and interactional asymmetry. Continue reading Mathematical approaches to the study of agents
World models: environment, agent and joint agent-environment models
A formal distinction between environment, agent, and joint agent-environment world models. Continue reading World models: environment, agent and joint agent-environment models
A Braitenberg vehicle’s habitat
A formal account of the environment or habitat associated with an agent. Continue reading A Braitenberg vehicle’s habitat
The Stream of Computation
The stream of computation and temporal continuity in artificial systems. Continue reading The Stream of Computation
Current projects (more)
Combining Physical and Intentional Stance for Safe AI
ARIA-funded work connecting physical dynamics with intentional descriptions of beliefs and goals to support verifiable, safer AI. Continue reading Combining Physical and Intentional Stance for Safe AI
A Bayesian Interpretation of the Internal Model Principle
How do we connect “internal models” in control to “Bayesian models” in cognitive science? Continue reading A Bayesian Interpretation of the Internal Model Principle