Experiments with Infinite-Horizon, Policy-Gradient Estimation
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
In this paper, we present algorithms that perform gradient ascent of the average reward in a partially observable Markov decision process (POMDP). These algorithms are based on GPOMDP, an algorithm introduced in a companion paper (Baxter & Bartlett, this volume), which computes biased estimates of the performance gradient in POMDPs. The algorithm's chief advantages are that it uses only one free parameter beta, which has a natural interpretation in terms of bias-variance trade-off, it requires no knowledge of the underlying state, and it can be applied to infinite state, control and observation spaces. We show how the gradient estimates produced by GPOMDP can be used to perform gradient ascent, both with a traditional stochastic-gradient algorithm, and with an algorithm based on conjugate-gradients that utilizes gradient information to bracket maxima in line searches. Experimental results are presented illustrating both the theoretical results of (Baxter & Bartlett, this volume) on a toy problem, and practical aspects of the algorithms on a number of more realistic problems.
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
Learning to predict by the methods of temporal differences
Sutton, R. S. (1988) · Machine Learning · doi:10.1007/bf00115009 · Cited by 5,148
Some Studies in Machine Learning Using the Game of Checkers
Samuel, A. L. (1959) · IBM Journal of Research and Development · doi:10.1147/rd.33.0210 · Cited by 4,443
Some studies in machine learning using the game of checkers
Samuel, A. L. (2000) · IBM Journal of Research and Development · doi:10.1147/rd.441.0206 · Cited by 1,439
Simple statistical gradient-following algorithms for connectionist reinforcement learning
Williams, R. J. (1992) · Machine Learning · doi:10.1023/a:1022672621406 · Cited by 817
Cited by
A Tutorial on the Cross-Entropy Method
de Boer, P.-T., Kroese, D. P., Mannor, S., & Rubinstein, R. Y. (2005) · Annals of Operations Research · doi:10.1007/s10479-005-5724-z · Cited by 3,024
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
Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., ODoherty, J., & Pezzulo, G. (2016) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2016.06.022 · Cited by 674
Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity
Florian, R. V. (2007) · Neural Computation · doi:10.1162/neco.2007.19.6.1468 · Cited by 358
Traffic light control using deep policy‐gradient and value‐function‐based reinforcement learning
Mousavi, S. S., Schukat, M., & Howley, E. (2017) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2017.0153 · Cited by 354
Cooperative Adaptive Cruise Control: A Reinforcement Learning Approach
Desjardins, C., & Chaib-draa, B. (2011) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2011.2157145 · Cited by 344
Partially Observable Markov Decision Processes
Spaan, M. T. J. (2012) · Adaptation, Learning, and Optimization · doi:10.1007/978-3-642-27645-3_12 · Cited by 315
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Greensmith, E., Bartlett, P. L., & Baxter, J. (2004) · doi:10.5555/1005332.1044710 · Cited by 300
Self-citationGiuliani, M., Castelletti, A., Pianosi, F., Mason, E., & Reed, P. M. (2016) · Journal of Water Resources Planning and Management · doi:10.1061/(asce)wr.1943-5452.0000570 · Cited by 257
Active inference and agency: optimal control without cost functions
Friston, K., Samothrakis, S., & Montague, R. (2012) · Biological Cybernetics · doi:10.1007/s00422-012-0512-8 · Cited by 241
“In direct policy searches e.g., (Williams 1992; Baxter et al. 2001), a policy is optimised by mapping each state directly to an action, without reference to the value of the state.”
BackgroundHoang, D. T., Wang, P., Niyato, D., & Hossain, E. (2017) · IEEE Access · doi:10.1109/access.2017.2649042 · Cited by 167
“1) Parameterized policy: We consider a randomized parameterized policy which is well studied in the literature [51], [52], [53].”
Background
Metadata
- Authors
- Baxter, J., Bartlett, P. L., & Weaver, L.
- Venue
- Journal of Artificial Intelligence Research
- Publisher
- AI Access Foundation
- Published
- 2001-11-01
- Volume
- 15
- Pages
- 351-381
- ISSN
- 1076-9757 (ISSN-L)
- OpenAlex
- W1814308503
- Cited by
- 137
- References
- 4
- FWCI
- 4.88
- Type
- journal article
- Language
- en
- Open access
- diamond
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
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.