Learning From Explanations Using Sentiment and Advice in RL
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
In order for robots to learn from people with no machine learning expertise, robots should learn from natural human instruction. Most machine learning techniques that incorporate explanations require people to use a limited vocabulary and provide state information, even if it is not intuitive. This paper discusses a software agent that learned to play the Mario Bros. game using explanations. Our goals to improve learning from explanations were twofold: (1) to filter explanations into advice and warnings and (2) to learn policies from sentences without state information. We used sentiment analysis to filter explanations into advice of what to do and warnings of what to avoid. We developed object-focused advice to represent what actions the agent should take when dealing with objects. A reinforcement learning agent used object-focused advice to learn policies that maximized its reward. After mitigating false negatives, using sentiment as a filter was approximately 85% accurate. object-focused advice performed better than when no advice was given, the agent learned where to apply the advice, and the agent could recover from adversarial advice. We also found the method of interaction should be designed to ease the cognitive load of the human teacher or the advice may be of poor quality.
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
Opinion mining and sentiment analysis
Pang, B., & Lee, L. (2008) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000011 · Cited by 6,372
A survey of robot learning from demonstration
Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.10.024 · Cited by 3,227
Research works printed but not linked: 20
- kuhlmann, 2004, Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer, Proceedings of the AAAI Workshop on Supervisory Control of Learning and Adaptive Systems
- 10.15607/RSS.2015.XI.018 · DOI
- maclin, 2005, Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression, Proc Nat Conf Artif Intell, 20, 819
- 10.3115/v1/P14-5010 · DOI · Paper page
- meriçli, 2014, An interactive approach for situated task specification through verbal instructions, Proc Int Conf Auton Agents and Multi Agent Syst, 1069
- 10.3115/1219840.1219855 · DOI · Paper page
- sivamurugan, 2012, Instructing a reinforcement learner, Proc FLAIRS Conf
- skinner, 1938, The Behavior of Organisms An Experimental Analysis
- 10.1126/science.7244649 · DOI · Paper page
- 10.2200/S00568ED1V01Y201402AIM028 · DOI
- 10.1145/1390156.1390187 · DOI · Paper page
- cobo, 2013, Object focused Q-learning for autonomous agents, Proc Int Conf Auton Agents and Multi Agent Syst, 1061
- 10.1109/ICTAI.2012.152 · DOI
- griffith, 2013, Policy shaping: Integrating human feedback with reinforcement learning, Proc Adv Neural Inf Process Syst, 2625
- 10.1109/IROS.2008.4651020 · DOI
- 10.1145/1015330.1015430 · DOI · Paper page
- krening, 2016, Object-focused advice in reinforcement learning, Proc Int Conf Auton Agents and Multi Agent Syst, 1447
- socher, 2013, Recursive deep models for semantic compositionality over a sentiment treebank, Proc Conf Empir Methods Nat Lang Process (EMNLP), 1631, 1631
- 10.1109/CEC.2010.5586133 · DOI
- sutton, 1998, Reinforcement Learning An Introduction, 1
Cited by
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
“Though it could be significantly complex and costly, most recent works done in XAI field belong to post-hoc class, it includes natural language explanations [71], visualizations of learned models [72], and explanations by example [73].”
BackgroundLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
The Mythos of Model Interpretability
Lipton, Z. C. (2016) · arXiv · doi:10.48550/arxiv.1606.03490 · Cited by 5,422
“As humans, we are known to engage in this behavior, as evidenced in hiring practices and college admissions.”
Background
Metadata
- Authors
- Krening, S., Harrison, B., Feigh, K. M., Isbell, C. L., Riedl, M., & Thomaz, A.
- Venue
- IEEE Transactions on Cognitive and Developmental Systems
- Published
- 2017-03
- Volume
- 9
- Issue
- 1
- Pages
- 44-55
- ISSN
- 2379-8920 (ISSN-L)
- 2379-8939
- OpenAlex
- W2549514639
- Cited by
- 84
- References
- 2
- FWCI
- 8.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Funders
- ONR (N000141410003)
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: Learning From Explanations Using Sentiment and Advice in RL. https://app.cochat.ai/papers/10.1109/tcds.2016.2628365
- The paper
- Krening, S., Harrison, B., Feigh, K. M., Isbell, C. L., Riedl, M., & Thomaz, A. (2017). Learning From Explanations Using Sentiment and Advice in RL. IEEE Transactions on Cognitive and Developmental Systems. https://doi.org/10.1109/tcds.2016.2628365
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.