Modulation Of Temporal Decision-making In A Deep Reinforcement Learning Agent Under The Dual-task Paradigm

Abstract

This study explores the interference in temporal processing within a dual-task paradigm from an artificial intelligence (AI) perspective. In this context, the dual-task setup is implemented as a simplified version of the Overcooked environment with two variations, single task (T) and dual task (T+N). Both variations involve an embedded time production task, but the dual task (T+N) additionally involves a concurrent number comparison task. Two deep reinforcement learning (DRL) agents were separately trained for each of these tasks. These agents exhibited emergent behavior consistent with human timing research. Specifically, the dual task (T+N) agent exhibited significant overproduction of time relative to its single task (T) counterpart. This result was consistent across four target durations. Preliminary analysis of neural dynamics in the agents' LSTM layers did not reveal any clear evidence of a dedicated or intrinsic timer. Hence, further investigation is needed to better understand

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypednekar2025modulation

Related papers

• Emergent Time-keeping Mechanisms In A Deep Reinforcement Learning Agent Performing An Interval Timing Task (2025)0.00
• Interval Timing In Deep Reinforcement Learning Agents (2019)0.00
• TD Or Not TD: Analyzing The Role Of Temporal Differencing In Deep Reinforcement Learning (2018)0.00
• Optimizing Attention And Cognitive Control Costs Using Temporally-layered Architectures (2023)2.26
• Dual-gated Epistemic Time-dilation: Autonomous Compute Modulation In Asynchronous MARL (2026)0.00
• On The Effect Of Auxiliary Tasks On Representation Dynamics (2021)0.00
• Adaptive Action Duration With Contextual Bandits For Deep Reinforcement Learning In Dynamic Environments (2025)0.00
• Hierarchical Reinforcement Learning As A Model Of Human Task Interleaving (2020)0.00