Value Iteration Networks
Open accessAbstract
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiable approximation of the value-iteration algorithm, which can be represented as a convolutional neural network, and trained end-to-end using standard backpropagation.We evaluate VIN based policies on discrete and continuous path-planning domains, and on a natural-language based search task. We show that by learning an explicit planning computation, VIN policies generalize better to new, unseen domains.This paper is a significantly abridged and IJCAI audience targeted version of the original NIPS 2016 paper with the same title, available here: https://arxiv.org/abs/1602.02867
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Bellman, R. E. (2010) · doi:10.1515/9781400835386 · Cited by 14,588 · see citing works
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248 · see citing works
Learning Hierarchical Features for Scene Labeling
Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.231 · Cited by 2,620 · see citing works
Sung, J., Jin, S. H., & Saxena, A. (2018) · Springer Proceedings in Advanced Robotics · doi:10.1007/978-3-319-60916-4_40 · Cited by 52 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Deep Reinforcement Learning: An Overview
Li, Y. (2017) · arXiv · doi:10.48550/arxiv.1701.07274 · Cited by 762 · see citing works
Learning to reinforcement learn
Wang, J. X., Kurth-Nelson, Z., Tirumala, D., Soyer, H., Leibo, J. Z., Munos, R., Blundell, C., Kumaran, D., & Botvinick, M. (2016) · arXiv · doi:10.48550/arxiv.1611.05763 · Cited by 579 · see citing works
Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review
Liu, R., Nageotte, F., Zanne, P., de Mathelin, M., & Dresp-Langley, B. (2021) · Robotics · doi:10.3390/robotics10010022 · Cited by 188 · see citing works
Neural Map: Structured Memory for Deep Reinforcement Learning
Parisotto, E., & Salakhutdinov, R. (2017) · arXiv · doi:10.48550/arxiv.1702.08360 · Cited by 178 · see citing works
Survey on reinforcement learning for language processing
Uc-Cetina, V., Navarro-Guerrero, N., Martin-Gonzalez, A., Weber, C., & Wermter, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10205-5 · Cited by 177 · see citing works
Meta-learned models of cognition
Binz, M., Dasgupta, I., Jagadish, A. K., Botvinick, M., Wang, J. X., & Schulz, E. (2024) · Behavioral and Brain Sciences · doi:10.1017/s0140525x23003266 · Cited by 38 · see citing works
A Comprehensive Review of Path-Planning Algorithms for Planetary Rover Exploration
Miao, Q., & Wei, G. (2025) · Remote Sensing · doi:10.3390/rs17111924 · Cited by 13
Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning
Yue, Y., Kang, B., Xu, Z., Huang, G., & Yan, S. (2022) · arXiv · doi:10.48550/arxiv.2206.12542 · Cited by 4
“Several empirically successful works like VPN [31], VIN [37] and MuZero [32] can be viewed as the instances that follow the value equivalence principle when considering diverse forms of Bellman operators and value approximations.”
BackgroundPlanetary Terrain Datasets and Benchmarks for Rover Path Planning
Chancán, M., Banerjee, A., & Nikolakopoulos, G. (2025) · arXiv · doi:10.48550/arxiv.2512.21438
“In VIN, the authors used a single DTM to generate 128 × 128 image patches and obtain occupancy grids for training/testing purposes.”
Influential
- Authors
- Tamar, A., Wu, Y., Thomas, G., Levine, S., & Abbeel, P.
- Affiliations
- University of California, Berkeley (US)
- OpenAI (United States) (US)
- Venue
- Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
- Published
- 2017-08
- Volume
- 29
- Pages
- 4949-4953
- OpenAlex
- W2258731934
- Cited by
- 484
- References
- 4
- Citations by year
- 2026: 8 · 2025: 21 · 2024: 27 · 2023: 36 · 2022: 46 · 2021: 72 · 2020: 79 · 2019: 88 · 2018: 63 · 2017: 37 · 2016: 7
- FWCI
- 33.30
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1351028, CAREER)
- Defense Advanced Research Projects Agency (FA8750, FA8750-14-C-0011)
- Office of Naval Research
- Army Research Office
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Keywords
- value iteration, reinforcement learning policy, path planning, natural language search, end-to-end learning
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
