The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Interactively shaping agents via human reinforcement: the TAMER framework
Abstract
As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample complexity of learning a task is knowledge transfer from humans to agents. Ideally, methods of transfer should be accessible to anyone with task knowledge, regardless of that person's expertise in programming and AI. This paper focuses on allowing a human trainer to interactively shape an agent's policy via reinforcement signals. Specifically, the paper introduces "Training an Agent Manually via Evaluative Reinforcement," or TAMER, a framework that enables such shaping. Differing from previous approaches to interactive shaping, a TAMER agent models the human's reinforcement and exploits its model by choosing actions expected to be most highly reinforced. Results from two domains demonstrate that lay users can train TAMER agents without defining an environmental reward function (as in an MDP) and indicate that human training within the TAMER framework can reduce sample complexity over autonomous learning algorithms.
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
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Introduction to Reinforcement Learning
Sutton, R. S., & Barto, A. G. (1998) · The MIT Press eBooks · Cited by 6,855
(2012) · Encyclopedia of the Sciences of Learning · doi:10.1007/978-1-4419-1428-6_5086 · Cited by 3,515
Apprenticeship learning via inverse reinforcement learning
Abbeel, P., & Ng, A. Y. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015430 · Cited by 2,769
Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
Ng, A. Y., Harada, D., & Russell, S. (1999) · Cited by 1,744
Neuro-Dynamic Programming: NDP
Bertsekas, D. P. (2001) · Encyclopedia of Optimization · doi:10.1007/0-306-48332-7_333 · Cited by 1,466
Robot Programming by Demonstration
Billard, A., Calinon, S., Dillmann, R., & Schaal, S. (2008) · Springer Handbook of Robotics · doi:10.1007/978-3-540-30301-5_60 · Cited by 1,002
Learning and Behavior: A Contemporary Synthesis
Bouton, M. E. (2006) · Cited by 509
Analysis of response time distributions in the study of cognitive processes.
Hockley, W. E. (1984) · Journal of Experimental Psychology: Learning, Memory, and Cognition · doi:10.1037//0278-7393.10.4.598 · Cited by 282
Thomaz, A. L., & Breazeal, C. (2006) · Cited by 259
Cited by
(2015) · Journal of Machine Learning Research · Cited by 1,119
Deep reinforcement learning from human preferences
Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017) · arXiv · doi:10.48550/arxiv.1706.03741 · Cited by 1,058
“MacGlashan et al. (2017), Pilarski et al. (2011), Knox and Stone (2009), and Knox (2012) perform experiments involving reinforcement learning from actual human feedback, although their algorithmic approach is less similar.”
Backgroundvon Rueden, L., Mayer, S., Beckh, K., Georgiev, B., Giesselbach, S., Heese, R., Kirsch, B., Walczak, M., Pfrommer, J., Pick, A., et al. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3079836 · Cited by 793
Reinforcement learning improves behaviour from evaluative feedback
Littman, M. L. (2015) · Nature · doi:10.1038/nature14540 · Cited by 368
A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems
Silva, F. L. D., & Costa, A. H. R. (2019) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11396 · Cited by 273
Shared Autonomy via Deep Reinforcement Learning
Reddy, S., Dragan, A., & Levine, S. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.005 · Cited by 175
Interactive Learning from Policy-Dependent Human Feedback
MacGlashan, J., Ho, M. K., Loftin, R., Peng, B., Wang, G., Roberts, D., Taylor, M. E., & Littman, M. L. (2017) · arXiv · doi:10.48550/arxiv.1701.06049 · Cited by 163
Prompt Engineering for Healthcare: Methodologies and Applications
Wang, J., Shi, E., Yu, S., Wu, Z., Ma, C., Dai, H., Yang, Q., Kang, Y., Wu, J., Hu, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.14670 · Cited by 150
Scalable agent alignment via reward modeling: a research direction
Leike, J., Krueger, D., Everitt, T., Martic, M., Maini, V., & Legg, S. (2018) · arXiv · doi:10.48550/arxiv.1811.07871 · Cited by 121
“…& Ng, 2004; Argall et al., 2009); providing feedback in the form of scores (El Asri et al., 2016), actions (Griffith et al., 2013), value (Knox & Stone, 2009), advantage (MacGlashan et al., 2017), or preferences over trajectories (Fürnkranz et al., 2012; Akrour et al., 2012, 2014; Wirth et…”
BackgroundReward learning from human preferences and demonstrations in Atari
Ibarz, B., Leike, J., Pohlen, T., Irving, G., Legg, S., & Amodei, D. (2018) · arXiv · doi:10.48550/arxiv.1811.06521 · Cited by 117
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Casper, S., Davies, X., Shi, C., Gilbert, T. K., Scheurer, J., Rando, J., Freedman, R., Korbak, T., Lindner, D., Freire, P., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.15217 · Cited by 101
Everitt, T., Hutter, M., Kumar, R., & Krakovna, V. (2021) · Synthese · doi:10.1007/s11229-021-03141-4 · Cited by 80
A Survey of Reinforcement Learning from Human Feedback
Kaufmann, T., Weng, P., Bengs, V., & Hüllermeier, E. (2023) · arXiv · doi:10.48550/arxiv.2312.14925 · Cited by 43
Kreutzer, J., Uyheng, J., & Riezler, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1165 · Cited by 38
Human-in-the-loop reinforcement learning in continuous-action space
Luo, B., Wu, Z., Zhou, F., & Wang, B.-C. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3289315 · Cited by 41
Supervising strong learners by amplifying weak experts
Christiano, P., Shlegeris, B., & Amodei, D. (2018) · arXiv · doi:10.48550/arxiv.1810.08575 · Cited by 39
Blind spot detection for safe sim-to-real transfer
Ramakrishnan, R., Kamar, E., Dey, D., Horvitz, E., & Shah, J. (2020) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11436 · Cited by 21
Metadata
- Authors
- Knox, W. B., & Stone, P.
- Venue
- Proceedings of the fifth international conference on Knowledge capture
- Publisher
- ACM
- Published
- 2009-09
- Pages
- 9-16
- OpenAlex
- W2156869222
- Cited by
- 406
- References
- 21
- FWCI
- 7.05
- Type
- conference paper
- 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
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.