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

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Amrapali Pednekar, Alvaro Garrido-Perez, Yara Khaluf, Pieter Simoens
• Venue: arXiv: cs.AI
• Published: 2026-08-17
• Collected: 2026-08-18
• URL: http://arxiv.org/abs/2608.16666v1
• PDF: https://arxiv.org/pdf/2608.16666v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The paper introduces Chronocooked, a benchmark suite for studying how reinforcement learning (RL) agents make decisions over time. It's inspired by Overcooked and includes cooking scenarios that require temporal decision making. The tasks are designed such that the critical temporal information is unobserved. The environment is simple to enable controlled experiments and support biologically plausible models. Baseline results are provided using three different models: non-recurrent, recurrent, and biologically plausible. This work aims to highlight the importance of incorporating time perception in artificial agents for human-robot interaction and applications in time-dependent societies.

What the Document Says

• The paper introduces Chronocooked, a reinforcement learning benchmark suite.
• It's inspired by Overcooked and includes cooking scenarios requiring temporal decision making.
• Tasks are designed such that critical temporal information is unobserved.
• Environment is kept simple for controlled experiments and biologically plausible models.
• Evaluation metrics expose limitations in timing abilities of RL agents.
• Baselines using a non-recurrent, recurrent, and biologically plausible model are reported.

Key Concepts Mentioned

• Reinforcement Learning
• Chronocooked
• Overcooked
• Temporal Decision Making
• Evaluation Metrics
• Biologically Plausible Models

Claims Made by the Document

• Chronocooked is a useful benchmark for studying implicit interval timing in RL agents.
• The benchmark can help underscore the need to incorporate time perception and temporal processing in artificial agents.

Evidence Used

• The paper presents Chronocooked and its design.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.