Incremental Self-Improvement for Life-Time Multi-Agent Reinforcement Learning
The DOI matches its Crossref record.
Abstract
Previous approaches to multi-agent reinforcement learning are either very limited or heuristic by nature. The main reason is: each agent's or "animat's" environment continually changes because the other learning animats keep changing. Traditional reinforcement learning algorithms cannot properly deal with this. Their convergence theorems require repeatable trials and strong (typically Markovian) assumptions about the environment. In this paper, however, we use a novel, general, sound method for multiple, reinforcement learning "animats", each living a single life with limited computational resources in an unrestricted, changing environment. The method is called "incremental self-improvement" (IS --- Schmidhuber, 1994). IS properly takes into account that whatever some animat learns at some point may affect learning conditions for other animats or for itself at any later point. The learning algorithm of an IS-based animat is embedded in its own policy --- the animat cannot only improve ...
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
Cited by
Planning and acting in partially observable stochastic domains
Kaelbling, L. P., Littman, M. L., & Cassandra, A. R. (1998) · Artificial Intelligence · doi:10.1016/s0004-3702(98)00023-x · Cited by 4,149
“Several techniques have been proposed recently for searching for good program-like controllers in pomdps [44, 21] We restrict our attention to the simpler nite-horizon case and a small set of in nite-horizon problems that have optimal nite-state plans.”
MethodCooperative Multi-Agent Learning: The State of the Art
Panait, L., & Luke, S. (2005) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-005-2631-2 · Cited by 1,237
“This idea was used in early multi-agent learning literature [228, 229, 312].”
MethodLayered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer
Stone, P. (2000) · The MIT Press eBooks · doi:10.7551/mitpress/4151.001.0001 · Cited by 380
Probabilistic Incremental Program Evolution
Salustowicz, R., & Schmidhuber, J. (1997) · Evolutionary Computation · doi:10.1162/evco.1997.5.2.123 · Cited by 249
Self-citationWortsman, M., Ramanujan, V., Liu, R., Kembhavi, A., Rastegari, M., Yosinski, J., & Farhadi, A. (2020) · arXiv · doi:10.48550/arxiv.2006.14769 · Cited by 144
Metadata
- Authors
- Zhao, J., & Schmidhuber, J.
- Venue
- From Animals to Animats 4
- Publisher
- The MIT Press
- Published
- 1996-08-26
- Pages
- 516-525
- OpenAlex
- W2556206701
- Cited by
- 24
- References
- 0
- FWCI
- 5.49
- Type
- book chapter
- Language
- en
- Open access
- closed
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: Incremental Self-Improvement for Life-Time Multi-Agent Reinforcement Learning. https://app.cochat.ai/papers/10.7551/mitpress/3118.003.0062
- The paper
- Zhao, J., & Schmidhuber, J. (1996). Incremental Self-Improvement for Life-Time Multi-Agent Reinforcement Learning. From Animals to Animats 4. https://doi.org/10.7551/mitpress/3118.003.0062
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.