Research
I study motor control in brains and machines by applying ideas from reinforcement learning and probabilistic machine learning. My research interests lie at the intersection of biological and machine learning.
|
Competitions
MyoChallenge 24: Physiological Dexterity and Agility in Bionic Humans
Team Muscle Heads: James Heald, Kai Biegun, Samo Hromadka, Maneesh Sahani
NeurIPS 2024 Competition Track Program
Our team came first place in the NeurIPS 2024 MyoChallenge Manipulation Track. The challenge involved coordinating a biologically-realistic arm with 63 muscles and a robotic prosthetic arm with 17 DoFs to transfer an object between two pillars. The object properties and pillar locations were randomized on each episode. To control the musculoskeletal arm, we trained a policy that recruited muscles in a coordinated manner using learned muscle synergies. This allowed us to efficiently acquire dexterous reaching and grasping skills. To control the robotic prosthetic arm, we combined a learned policy with inverse kinematic control, enabling smooth hand-offs and object relocation. Curriculum learning and reward shaping were used to solve the task in stages (reach, grasp, handover, move object to goal) .
|
Our winning solution, showcasing robustness to random pillar locations and object properties (weight, size and friction).
Our solution ranked first on all metrics: score, time, effort and peak contact force.
|
Select publications
Representative papers are highlighted.
|
|
The computational and neural bases of context-dependent learning
James Heald, Daniel Wolpert*, Máté Lengyel*
Annual Review of Neuroscience, 2023
We review a theoretical approach to formalizing context-dependent learning in the face of contextual uncertainty and the core computations it requires. We show how this approach organizes a large body of disparate experimental observations, from multiple levels of brain organization (including cells, circuits, systems and behavior) and multiple brain regions (most prominently the prefrontal cortex, the hippocampus and motor cortices), into a coherent framework. We argue that contextual inference may also be key to understanding continual learning in the brain.
|
|
Contextual inference in learning and memory
James Heald, Máté Lengyel*, Daniel Wolpert*
Trends in Cognitive Sciences, 2023   (Feature Review and Issue Cover)
PDF /
Issue Cover
In this issue of Trends in Cognitive Sciences, we review a computational framework of repertoire learning that provides a unifying account of phenomena across numerous domains, including conditioning, episodic memory, economic decision making and motor learning.
|
|
Contextual inference underlies the learning of sensorimotor repertoires
James Heald, Máté Lengyel*, Daniel Wolpert*
Nature, 2021   (accompanied by News and Views)
PDF /
Code /
Data /
New and Views
We develop a theory of motor learning based on the principle of contextual inference. Our theory reveals that adaptation can arise by both creating and updating memories and changing how existing memories are differentially expressed.
|
|
Multiple motor memories are learned to control different points on a tool
James Heald, James Ingram, J. Randall Flanagan, Daniel Wolpert
Nature Human Behaviour, 2018
PDF /
Code
Different parts of tools are often handled in different ways. This study presents a computational model explaining how humans build separate motor memories for different parts of the same object.
|
|