@article {5319, title = {The neural architecture of theory-based reinforcement learning}, journal = {Neuron}, volume = {111}, year = {2023}, month = {03/2023}, pages = {1331 - 1344.e8}, abstract = {

Humans learn internal models of the world that support planning and generalization in complex environments. Yet it remains unclear how such internal models are represented and learned in the brain. We approach this question using theory-based reinforcement learning, a strong form of model-based reinforcement learning in which the model is a kind of intuitive theory. We analyzed fMRI data from human participants learning to play Atari-style games. We found evidence of theory representations in prefrontal cortex and of theory updating in prefrontal cortex, occipital cortex, and fusiform gyrus. Theory updates coincided with transient strengthening of theory representations. Effective connectivity during theory updating suggests that information flows from prefrontal theory-coding regions to posterior theory-updating regions. Together, our results are consistent with a neural architecture in which top-down theory representations originating in prefrontal regions shape sensory predictions in visual areas, where factored theory prediction errors are computed and trigger bottom-up updates of the theory.

}, issn = {08966273}, doi = {10.1016/j.neuron.2023.01.023}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0896627323000739}, author = {Tomov, Momchil S. and Tsividis, Pedro A. and Pouncy, Thomas and Tenenbaum, Joshua B. and Gershman, Samuel J.} } @article {5292, title = {Inductive biases in theory-based reinforcement learning}, journal = {Cognitive Psychology}, volume = {138}, year = {2022}, month = {11/2022}, pages = {101509}, abstract = {

Understanding the inductive biases that allow humans to learn in complex environments has been an important goal of cognitive science. Yet, while we have discovered much about human biases in specific learning domains, much of this research has focused on simple tasks that lack the complexity of the real world. In contrast, video games involving agents and objects embedded in richly structured systems provide an experimentally tractable proxy for real-world complexity. Recent work has suggested that key aspects of human learning in domains like video games can be captured by model-based reinforcement learning (RL) with object-oriented relational models{\textemdash}what we term theory-based RL. Restricting the model class in this way provides an inductive bias that dramatically increases learning efficiency, but in this paper we show that humans employ a stronger set of biases in addition to syntactic constraints on the structure of theories. In particular, we catalog a set of semantic biases that constrain the content of theories. Building these semantic biases into a theory-based RL system produces more human-like learning in video game environments.

}, issn = {00100285}, doi = {10.1016/j.cogpsych.2022.101509}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0010028522000457}, author = {Pouncy, Thomas and Gershman, Samuel J.} } @article {4832, title = {What Is the Model in Model-Based Planning?}, journal = {Cognitive Science}, volume = {45}, year = {2021}, month = {01/2021}, abstract = {

Flexibility is one of the hallmarks of human problem-solving. In everyday life, people adapt to changes in common tasks with little to no additional training. Much of the existing work on flexibility in human problem-solving has focused on how people adapt to tasks in new domains by drawing on solutions from previously learned domains. In real-world tasks, however, humans must generalize across a wide range of within-domain variation. In this work we argue that representational abstraction plays an important role in such within-domain generalization. We then explore the nature of this representational abstraction in realistically complex tasks like video games by demonstrating how the same model-based planning framework produces distinct generalization behaviors under different classes of task representation. Finally, we compare the behavior of agents with these task representations to humans in a series of novel grid-based video game tasks. Our results provide evidence for the claim that within-domain flexibility in humans derives from task representations composed of propositional rules written in terms of objects and relational categories.

}, issn = {0364-0213}, doi = {10.1111/cogs.v45.110.1111/cogs.12928}, url = {https://onlinelibrary.wiley.com/toc/15516709/45/1}, author = {Pouncy, Thomas and Tsividis, Pedro and Samuel J Gershman} }