# From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning

arXiv: https://arxiv.org/abs/2011.04590 · HTML: https://mlsanity.com/paper/2011.04590/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [Streaming Deep Reinforcement Learning Finally Works](https://mlsanity.com/paper/2410.14606/) (2024)
- [Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning](https://mlsanity.com/paper/2302.06548/) (2023)
- [GVFs in the Real World: Making Predictions Online for Water Treatment](https://mlsanity.com/paper/2312.01624/) (2023)
- [Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks](https://mlsanity.com/paper/2302.05326/) (2023)
- [Real-Time Recurrent Learning using Trace Units in Reinforcement Learning](https://mlsanity.com/paper/2409.01449/) (2024)
- [Assessing Human Interaction in Virtual Reality With Continually Learning Prediction Agents Based on Reinforcement Learning Algorithms: A Pilot Study](https://mlsanity.com/paper/2112.07774/) (2021)
- [Agent-State Construction with Auxiliary Inputs](https://mlsanity.com/paper/2211.07805/) (2022)
- [Learning Agent State Online with Recurrent Generate-and-Test](https://mlsanity.com/paper/2112.15236/) (2021)
- [Pavlovian Signalling with General Value Functions in Agent-Agent Temporal Decision Making](https://mlsanity.com/paper/2201.03709/) (2022)
- [The Frost Hollow Experiments: Pavlovian Signalling as a Path to Coordination and Communication Between Agents](https://mlsanity.com/paper/2203.09498/) (2022)
- [Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning](https://mlsanity.com/paper/2605.16318/) (2026)
- [Swift-Sarsa: Fast and Robust Linear Control](https://mlsanity.com/paper/2507.19539/) (2025)
- [Forager: a lightweight testbed for continual learning with partial observability in RL](https://mlsanity.com/paper/2605.01131/) (2026)

## Abstract (arXiv)

We present three new diagnostic prediction problems inspired by classical-conditioning experiments to facilitate research in online prediction learning. Experiments in classical conditioning show that animals such as rabbits, pigeons, and dogs can make long temporal associations that enable multi-step prediction. To replicate this remarkable ability, an agent must construct an internal state representation that summarizes its interaction history. Recurrent neural networks can automatically construct state and learn temporal associations. However, the current training methods are prohibitively expensive for online prediction -- continual learning on every time step -- which is the focus of this paper. Our proposed problems test the learning capabilities that animals readily exhibit and highlight the limitations of the current recurrent learning methods. While the proposed problems are nontrivial, they are still amenable to extensive testing and analysis in the small-compute regime, thereby enabling researchers to study issues in isolation, ultimately accelerating progress towards scalable online representation learning methods.