Interpretable Reinforcement Learning Inspired by Piaget's Theory of Cognitive Development

by   Aref Hakimzadeh, et al.

Endeavors for designing robots with human-level cognitive abilities have led to different categories of learning machines. According to Skinner's theory, reinforcement learning (RL) plays a key role in human intuition and cognition. Majority of the state-of-the-art methods including deep RL algorithms are strongly influenced by the connectionist viewpoint. Such algorithms can significantly benefit from theories of mind and learning in other disciplines. This paper entertains the idea that theories such as language of thought hypothesis (LOTH), script theory, and Piaget's cognitive development theory provide complementary approaches, which will enrich the RL field. Following this line of thinking, a general computational building block is proposed for Piaget's schema theory that supports the notions of productivity, systematicity, and inferential coherence as described by Fodor in contrast with the connectionism theory. Abstraction in the proposed method is completely upon the system itself and is not externally constrained by any predefined architecture. The whole process matches the Neisser's perceptual cycle model. Performed experiments on three typical control problems followed by behavioral analysis confirm the interpretability of the proposed method and its competitiveness compared to the state-of-the-art algorithms. Hence, the proposed framework can be viewed as a step towards achieving human-like cognition in artificial intelligent systems.



There are no comments yet.


page 1

page 8


Reinforcement Learning with Analogical Similarity to Guide Schema Induction and Attention

Research in analogical reasoning suggests that higher-order cognitive fu...

Hierarchical principles of embodied reinforcement learning: A review

Cognitive Psychology and related disciplines have identified several cri...

Social Neuro AI: Social Interaction as the "dark matter" of AI

We are making the case that empirical results from social psychology and...

Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions

Reinforcement learning (RL) agents in human-computer interactions applic...

The thermodynamic cost of fast thought

After more than sixty years, Shannon's research [1-3] continues to raise...

From self-tuning regulators to reinforcement learning and back again

Machine and reinforcement learning (RL) are being applied to plan and co...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.