Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents

2026-08-17

AI Summary

This study addresses the deficiency in implicit temporal perception and decision-making capabilities of reinforcement learning agents by proposing the first RL benchmark specifically designed for implicit interval timing. Leveraging the Overcooked environment, we construct tasks where temporal information is unobservable yet critical, alongside a multi-model evaluation framework and specialized timing metrics to systematically assess recurrent networks and biologically plausible models. Our findings reveal significant limitations in current agents' implicit temporal reasoning abilities. By filling a critical gap in existing benchmarks, this work provides essential support for advancing biologically plausible temporal modeling and evaluation methodologies within the field of reinforcement learning.

Abstract

This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal decision making. The tasks and reward functions are designed such that temporal information is unobserved yet critical for optimal performance. The environment is intentionally kept simple to enable controlled experiments and support biologically plausible models. Evaluation metrics are designed to expose limitations in timing abilities of RL agents, and we report baselines using a non-recurrent, a recurrent, and a biologically plausible model. This work ultimately aims to underscore the need to incorporate time perception and temporal processing in artificial agents designed for human robot interaction and deployment in time dependent human societies.

Problem

• Implicit Interval Timing
• Reinforcement Learning
• Temporal Decision Making
• Human-Robot Interaction

Innovation

• Implicit Interval Timing
• Reinforcement Learning Benchmark
• Biologically Plausible Models
• Temporal Decision Making
• Human-Robot Interaction