Recurrent policy gradients
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Reinforcement learning for partially observable Markov decision problems (POMDPs) is a challenge as it requires policies with an internal state. Traditional approaches suffer significantly from this shortcoming and usually make strong assumptions on the problem domain such as perfect system models, state-estimators and a Markovian hidden system. Recurrent neural networks (RNNs) offer a natural framework for dealing with policy learning using hidden state and require only few limiting assumptions. As they can be trained well using gradient descent, they are suited for policy gradient approaches. In this paper, we present a policy gradient method, the Recurrent Policy Gradient which constitutes a model-free reinforcement learning method. It is aimed at training limited-memory stochastic policies on problems which require long-term memories of past observations. The approach involves approximating a policy gradient for a recurrent neural network by backpropagating return-weighted characteristic eligibilities through time. Using a ‘‘Long Short-Term Memory’’ RNN architecture, we are able to outperform previous RL methods on three important benchmark tasks. Furthermore, we show that using history-dependent baselines helps reducing estimation variance significantly, thus enabling our approach to tackle more challenging, highly stochastic environments.
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-citationLearning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542
Backpropagation 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 · cited 1×
“Like conventional neural networks, they can be trained backpropagation through time (BPTT) [17, 22].”
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
Reinforcement learning of motor skills with policy gradients
Peters, J., & Schaal, S. (2008) · Neural Networks · doi:10.1016/j.neunet.2008.02.003 · Cited by 831
Self-citationSimple statistical gradient-following algorithms for connectionist reinforcement learning
Williams, R. J. (1992) · Machine Learning · doi:10.1023/a:1022672621406 · Cited by 817
Peters, J., & Schaal, S. (2008) · Neurocomputing · doi:10.1016/j.neucom.2007.11.026 · Cited by 738
Self-citation
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-citationDeep Reinforcement Learning: A Brief Survey
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2743240 · Cited by 4,733
“Note that RNNs are not restricted to value-function-based methods but have also been successfully applied to policy search [138] and actor-critic methods [36, 72].”
A Brief Survey of Deep Reinforcement Learning
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · arXiv · doi:10.48550/arxiv.1708.05866 · Cited by 4,733
Proximal Policy Optimization in StarCraft
Liu, Y. (2025) · doi:10.12794/metadc1505267 · Cited by 615
Cognitive Mapping and Planning for Visual Navigation
Gupta, S., Davidson, J., Levine, S., Sukthankar, R., & Malik, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.769 · Cited by 500
Metadata
- Authors
- Wierstra, D., Forster, A., Peters, J., & Schmidhuber, J.
- Venue
- Logic Journal of IGPL
- Publisher
- Oxford University Press (OUP)
- Published
- 2009-09-09
- Volume
- 18
- Issue
- 5
- Pages
- 620-634
- ISSN
- 1367-0751 (ISSN-L)
- 1368-9894
- OpenAlex
- W2103581399
- Cited by
- 105
- References
- 7
- FWCI
- 2.89
- Type
- journal article
- 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: Recurrent policy gradients. https://app.cochat.ai/papers/10.1093/jigpal/jzp049
- The paper
- Wierstra, D., Forster, A., Peters, J., & Schmidhuber, J. (2010). Recurrent policy gradients. Logic Journal of IGPL. https://doi.org/10.1093/jigpal/jzp049
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.