Learning From Explanations Using Sentiment and Advice in RL

IEEE Transactions on Cognitive and Developmental Systems

Volumn 9, Issue 1, 2017, Pages 44-55

  Krening, Samantha ^a   Harrison, Brent ^a   Feigh, Karen M ^a   Isbell, Charles Lee ^a   Riedl, Mark ^a   Thomaz, Andrea ^a  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Advice; reinforcement learning (RL); sentiment

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS; PASSIVE FILTERS; SOFTWARE AGENTS; TEACHING;

ADVICE; COGNITIVE LOADS; FALSE NEGATIVES; MACHINE LEARNING TECHNIQUES; REINFORCEMENT LEARNING AGENT; SENTIMENT; SENTIMENT ANALYSIS; STATE INFORMATION;

REINFORCEMENT LEARNING;

EID: 85015665009     PISSN: 23798920     EISSN: 23798939     Source Type: Journal    
DOI: 10.1109/TCDS.2016.2628365     Document Type: Article

References (22)

1. P. Abbeel and A. Y. Ng, "Apprenticeship learning via inverse reinforcement learning," in Proc. 21st Int. Conf. Mach. Learn., Banff, AB, Canada, 2004, p. 1.
2. B. D. Argall, B. Browning, and M. Veloso, "Learning robot motion control with demonstration and advice-operators," in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst. (IROS), Nice, France, 2008, pp. 399-404.
3. B. D. Argall, S. Chernova, M. Veloso, and B. Browning, "A survey of robot learning from demonstration," Robot. Auton. Syst., vol. 57, no. 5, pp. 469-483, 2009.
4. S. Chernova and A. L. Thomaz, "Robot learning from human teachers," Synth. Lectures Artif. Intell. Mach. Learn., vol. 8, no. 3, pp. 1-121, 2014.
5. L. C. Cobo, C. L. Isbell, and A. L. Thomaz, "Object focused Q-learning for autonomous agents," in Proc. Int. Conf. Auton. Agents Multi Agent Syst., St. Paul, MN, USA, 2013, pp. 1061-1068.
6. C. Diuk, A. Cohen, and M. L. Littman, "An object-oriented representation for efficient reinforcement learning," in Proc. 25th Int. Conf. Mach. Learn., Helsinki, Finland, 2008, pp. 240-247.
7. S. Griffith, K. Subramanian, J. Scholz, C. Isbell, and A. L. Thomaz, "Policy shaping: Integrating human feedback with reinforcement learning," in Proc. Adv. Neural Inf. Process. Syst., 2013, pp. 2625-2633.
8. M. Joshi, R. Khobragade, S. Sarda, U. Deshpande, and S. Mohan, "Object-oriented representation and hierarchical reinforcement learning in infinite mario," in Proc. IEEE 24th Int. Conf. Tools Artif. Intell. (ICTAI), vol. 1. Athens, Greece, 2012, pp. 1076-1081.
9. S. Krening, B. Harrison, K. M. Feigh, C. Isbell, and A. Thomaz, "Objectfocused advice in reinforcement learning," in Proc. Int. Conf. Auton. Agents Multi Agent Syst., Singapore, 2016, pp. 1447-1448.
10. G. Kuhlmann, P. Stone, R. Mooney, and J. Shavlik, "Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer," in Proc. AAAI Workshop Supervisory Control Learn. Adapt. Syst., San Jose, CA, USA, 2004.
11. J. MacGlashan et al., "Grounding English commands to reward functions," in Proc. Robot. Sci. Syst., Rome, Italy, Jul. 2015.
12. R. Maclin, J. Shavlik, L. Torrey, T. Walker, and E. Wild, "Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression," in Proc. Nat. Conf. Artif. Intell., vol. 20. Pittsburgh, PA, USA, 2005, pp. 819-824.
13. C. D. Manning et al., "The Stanford CoreNLP natural language processing toolkit," in Proc. 52nd Annu. Meeting Assoc. Comput. Linguist. Syst. Demonstrations, Baltimore, MD, USA, 2014, pp. 55-60.
14. C. Meriçli, S. D. Klee, J. Paparian, and M. Veloso, "An interactive approach for situated task specification through verbal instructions," in Proc. Int. Conf. Auton. Agents Multi Agent Syst., Paris, France, 2014, pp. 1069-1076.
15. B. Pang and L. Lee, "Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales," in Proc. 43rd Annu. Meeting Assoc. Comput. Linguist., Ann Arbor, MI, USA, 2005, pp. 115-124.
16. B. Pang and L. Lee, "Opinion mining and sentiment analysis," Found. Trends Inf. Retrieval, vol. 2, nos. 1-2, pp. 1-135, 2008.
17. M. S. Sivamurugan and B. Ravindran, "Instructing a reinforcement learner," in Proc. FLAIRS Conf., Marco Island, FL, USA, 2012.
18. B. F. Skinner, The Behavior of Organisms: An Experimental Analysis. New York, NY, USA: D. Appleton, 1938.
19. B. F. Skinner, "Selection by consequences," Science, vol. 213, no. 4507, pp. 501-504, 1981.
20. R. Socher et al., "Recursive deep models for semantic compositionality over a sentiment treebank," in Proc. Conf. Empir. Methods Nat. Lang. Process. (EMNLP), vol. 1631. Seattle, WA, USA, pp. 1631-1642, 2013.
21. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, vol. 1. Cambridge, MA, USA: MIT Press, 1998.
22. J. Togelius, S. Karakovskiy, and R. Baumgarten, "The 2009 Mario AI competition," in Proc. IEEE Congr. Evol. Comput. (CEC), Barcelona, Spain, 2010, pp. 1-8.