Co-evolving recurrent neurons learn deep memory POMDPs
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use in reinforcement learning environments. Neuroevolution, the evolution of artificial neural networks using genetic algorithms, can potentially solve real-world reinforcement learning tasks that require deep use of memory, i.e. memory spanning hundreds or thousands of inputs, by searching the space of recurrent neural networks directly. In this paper, we introduce a new neuroevolution algorithm called Hierarchical Enforced SubPopulations that simultaneously evolves networks at two levels of granularity: full networks and network components or neurons. We demonstrate the method in two POMDP tasks that involve temporal dependencies of up to thousands of time-steps, and show that it is faster and simpler than the current best conventional reinforcement learning system on these tasks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Self-citationBackpropagation through time: what it does and how to do it
Werbos, P. J. (1990) · Proceedings of the IEEE · doi:10.1109/5.58337 · Cited by 4,879
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369 · cited 1×
“Unfortunately, training RNNs with standard gradient-descent methods such as Real-Time Recurrent Learning (RTRL; [11, 14]) or Back Propagation Through Time (BPTT; [12]) is not possible when actions depend on inputs from more than as few as 10 time-steps in the past.”
Method
Cited by
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Self-citationApplication and theory gaps during the rise of artificial intelligence in education
Chen, X., Xie, H., Zou, D., & Hwang, G.-J. (2020) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2020.100002 · Cited by 1,003
Decision Making in Multiagent Systems: A Survey
Rizk, Y., Awad, M., & Tunstel, E. W. (2018) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2018.2840971 · Cited by 219
“These include RL, dynamic programming (DP), recurrent neural networks (RNNs), and evolutionary computing, to name a few.”
MethodISP Meets Deep Learning: A Survey on Deep Learning Methods for Image Signal Processing
Santos, C. F. G. D., Arrais, R. R., Silva, J. V. S. D., Silva, M. H. M. D., Neto, W. B. G. D. A., Lopes, L. T., Bileki, G. A., Lima, I. O., Rondon, L. B., Souza, B. M. D., et al. (2025) · ACM Computing Surveys · doi:10.1145/3708516 · Cited by 15
Metadata
- Authors
- Gomez, F. J., & Schmidhuber, J.
- Venue
- Proceedings of the 7th annual conference on Genetic and evolutionary computation
- Publisher
- ACM
- Published
- 2005-06-25
- Pages
- 491-498
- OpenAlex
- W2171625236
- Cited by
- 67
- References
- 3
- FWCI
- 3.58
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Co-evolving recurrent neurons learn deep memory POMDPs. https://app.cochat.ai/papers/10.1145/1068009.1068092
- The paper
- Gomez, F. J., & Schmidhuber, J. (2005). Co-evolving recurrent neurons learn deep memory POMDPs. Proceedings of the 7th annual conference on Genetic and evolutionary computation. https://doi.org/10.1145/1068009.1068092
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.