Emergent Time-keeping Mechanisms In A Deep Reinforcement Learning Agent Performing An Interval Timing Task

Abstract

Drawing parallels between Deep Artificial Neural Networks (DNNs) and biological systems can aid in understanding complex biological mechanisms that are difficult to disentangle. Temporal processing, an extensively researched topic, is one such example that lacks a coherent understanding of its underlying mechanisms. In this study, we investigate temporal processing in a Deep Reinforcement Learning (DRL) agent performing an interval timing task and explore potential biological counterparts to its emergent behavior. The agent was successfully trained to perform a duration production task, which involved marking successive occurrences of a target interval while viewing a video sequence. Analysis of the agent's internal states revealed oscillatory neural activations, a ubiquitous pattern in biological systems. Interestingly, the agent's actions were predominantly influenced by neurons exhibiting these oscillations with high amplitudes and frequencies corresponding to the target interval. P

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypednekar2025emergent

Related papers

• Interval Timing In Deep Reinforcement Learning Agents (2019)0.00
• Modulation Of Temporal Decision-making In A Deep Reinforcement Learning Agent Under The Dual-task Paradigm (2025)0.00
• Emergence Of Adaptive Circadian Rhythms In Deep Reinforcement Learning (2023)0.00
• Deep Reinforcement Learning With Time-scale Invariant Memory (2024)0.00
• Learning When To Act: Interval-aware Reinforcement Learning With Predictive Temporal Structure (2026)0.00
• Teaching Robots To Perceive Time -- A Reinforcement Learning Approach (extended Version) (2019)0.00
• An Introduction To Reinforcement Learning For Neuroscience (2023)5.84
• Learning Sparse Representations In Reinforcement Learning (2019)0.00