DeepAI AI Chat
Log In Sign Up

Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning

by   Mark Edmonds, et al.

Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a common abstract structure that is invariant across domains, and (ii) the behavior of specific features of the environment remain constant across domains. We adopt a Bayesian perspective of causal theory induction and use these theories to transfer knowledge between environments. Given these general theories, the goal is to train an agent by interactively exploring the problem space to (i) discover, form, and transfer useful abstract and structural knowledge, and (ii) induce useful knowledge from the instance-level attributes observed in the environment. A hierarchy of Bayesian structures is used to model abstract-level structural causal knowledge, and an instance-level associative learning scheme learns which specific objects can be used to induce state changes through interaction. This model-learning scheme is then integrated with a model-based planner to achieve a task in the OpenLock environment, a virtual “escape room” with a complex hierarchy that requires agents to reason about an abstract, generalized causal structure. We compare performances against a set of predominate model-free reinforcement learning(RL) algorithms. RL agents showed poor ability transferring learned knowledge across different trials. Whereas the proposed model revealed similar performance trends as human learners, and more importantly, demonstrated transfer behavior across trials and learning situations.


page 1

page 2

page 3

page 4


Structure Mapping for Transferability of Causal Models

Human beings learn causal models and constantly use them to transfer kno...

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

Inducing causal relationships from observations is a classic problem in ...

Grounding Hierarchical Reinforcement Learning Models for Knowledge Transfer

Methods of deep machine learning enable to to reuse low-level representa...

Learning Social Learning

Social learning is a key component of human and animal intelligence. By ...

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Despite recent successes of reinforcement learning (RL), it remains a ch...

Intrinsically Motivated Learning of Causal World Models

Despite the recent progress in deep learning and reinforcement learning,...

Formalizing Falsification of Causal Structure Theories for Consciousness Across Computational Hierarchies

There is currently a global, multimillion-dollar effort to experimentall...