Learning From Explanations Using Sentiment and Advice in RL

By Samantha Krening, Brent Harrison, K. Feigh, Charles Lee Isbell Jr., Mark O. Riedl, Andrea Lockerd Thomaz. 2017

76 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Reinforcement Learning

Citations in the corpus

Training Classifiers with Natural Language Explanations (2018, methodology): “Finally, while we have used natural language explanations as input to train models, they can also be output to interpret models (Krening et al., 2017; Lei et al., 2016).”
Grounded Language Learning in a Simulated 3D World (2017, background): “…unsurprisingly, the few systems that attempt to learn language grounding in artiﬁcial agents do so with respect to environments that are far simpler than the continuous, noisy sensory experience encountered by humans (Steels, 2008; Roy and Pentland, 2002; Krening et al., 2016; Yu et al., 2017).”
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Informativeness [5, 44, 21, 25, 26, 45, 30, 32, 34, 35, 37, 38, 41, 46, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 63, 64, 65, 66, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 86, 87, 88, 89, 59, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 1”
The mythos of model interpretability (2016, background): “As humans, we are known to engage in this behavior, as evidenced in hiring practices and college admissions.”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “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].”
Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation (2020, background): “resort to human explanatory advice in natural language [19, 48].”
Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, background): “The work in [119] provides a starting point, which presents an agent who trained to simulates the Mario Bros.”
A Study of Automatic Metrics for the Evaluation of Natural Language Explanations (2021, background): “Explanations are a core component of human interaction (Scalise et al., 2017; Krening et al., 2017; Madumal et al., 2019).”
Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems (2021, unknown): “Object-oriented symbolic interfaces like these have also been used in other previous works to allow humans to provide informative and generalizable object-focused advices in an effortless way (Thomaz, Breazeal et al. 2006; Krening et al. 2016; Guan et al. 2021).”
Auditing Deep Learning processes through Kernel-based Explanatory Models (2019, methodology): “Another strategy is pairing the decision model with a generative model to produce verbose explanations (Krening et al., 2017).”
Guiding Reinforcement Learning Exploration Using Natural Language (2017, unknown): “A I] 14 S e p 2017 or directly critique the agent’s behavior (Loftin et al. 2014; Grifﬁth et al. 2013; Cederborg et al. 2015).”
Interpretable Machine Learning in Healthcare (2018, methodology): “Interpretability of ML models is applicable across all types of ML: supervised learning [17], unsupervised learning [6] and reinforcement learning [15].”
Bridging the Gap: Converting Human Advice into Imagined Examples (2019, background): “Krening et al. (2017) look at object-focused advice, which is essentially translated into policies whose recommendations are balanced against those based on learned object-oriented policies.”
Robots That Use Language (2020, background): “(114) used object-focused advice provided by people to improve the learning speed of an agent.”