George Konidaris
Director: Intelligent Robot Lab
Assistant Professor
Department of Computer Science
Department of Electrical & Computer Engineering
Duke University, Durham NC

Publications

You can filter the publications by keyword, listed in reverse chronological order (most recent first).

  
2016
  1. S. Murray, W. Floyd-Jones, Y. Qi, G.D. Konidaris and D. Sorin. The Microarchitecture of a Real-Time Robot Motion Planning Accelerator. To appear, Proceedings of the The 49th Annual IEEE/ACM International Symposium on Microarchitecture, October 2016.

  2. G.D. Konidaris. Constructing Abstraction Hierarchies Using a Skill-Symbol Loop. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, July 2016.

  3. F. Doshi-Velez and G.D. Konidaris. Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, July 2016.

  4. S. James, B. Rosman and G.D. Konidaris. An Investigation into the Effectiveness of Heavy Rollouts in UCT. In the IJCAI 2016 Workshop on General Intelligence in Game-Playing Agents, July 2016.

  5. S. Murray, W. Floyd-Jones, Y. Qi, D. Sorin and G.D. Konidaris. Robot Motion Planning on a Chip. Accepted, Robotics: Science and Systems XII, June 2016.

  6. Y. Zhou and G.D. Konidaris. Representing and Learning Complex Object Interactions. Accepted, Robotics: Science and Systems XII, June 2016.

  7. B. Burchfiel and G.D. Konidaris. Generalized 3D Object Representation using Bayesian Eigenobjects. In the RSS 2016 Workshop on Geometry and Beyond: Representations, Physics, and Scene Understanding for Robotics, June 2016.

  8. W. Masson, P. Ranchod, and G.D. Konidaris. Reinforcement Learning with Parameterized Actions. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 2016.

2015
  1. G.D. Konidaris. What Are Representations For? Invited contribution in IEEE CIS Newsletter on Cognitive and Developmental Systems, page 7, December 2015.

  2. P. S. Thomas, S. Niekum, G. Theocharous, and G. D. Konidaris. Policy Evaluation using the Ω-Return. In Advances in Neural Information Processing Systems 28, pages 334-342, December 2015.

  3. D.H. Zewdie and G.D. Konidaris. Representation Discovery for Kernel-Based Reinforcement Learning. Technical Report MIT-CSAIL-TR-2015-032, MIT Computer Science and Artificial Intelligence Laboratory, November 2015.

  4. G.D. Konidaris. Constructing Abstraction Hierarchies Using a Skill-Symbol Loop. ArXiv:1509.07582.

  5. P. Ranchod, B. Rosman, G.D. Konidaris. Nonparametric Bayesian Reward Segmentation for Skill Discovery Using Inverse Reinforcement Learning. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 471-477, September 2015.

  6. D. Wookey and G.D. Konidaris. Regularized Feature Selection in Reinforcement Learning. (Freely accessible draft.) Machine Learning, 100(2), 655-676, September 2015.

  7. G.D. Konidaris, L.P. Kaelbling, and T. Lozano-Perez. Symbol Acquisition for Probabilistic High-Level Planning. In Proceedings of the Twenty Fourth International Joint Conference on Artificial Intelligence, pages 3619-3627, July 2015.

  8. C. Amato, G.D. Konidaris, A. Anders, G. Cruz, J.P. How, and L.P. Kaelbling. Policy Search for Multi-Robot Coordination under Uncertainty. In Robotics: Science and Systems XI, pages , July 2015.

  9. C. Amato, S. Omidshafiei, A Agha-mohammadi, G.D. Konidaris, J.P. How, and L.P. Kaelbling. Probabilistic Planning for Multi-Robot Systems. In Proceedings of the RSS-2015 Workshop on Principles of Multi-Robot Systems, July 2015.

  10. C. Amato, G.D. Konidaris, G. Cruz, C. Maynor, J.P. How, and L.P. Kaelbling. Planning for Decentralized Control of Multiple Robots Under Uncertainty. In Proceedings of the 2015 IEEE International Conference on Robotics and Automation, pages 1241-1248, May 2015.

  11. S. Niekum, S. Osentoski, G.D.Konidaris, S. Chitta, B. Marthi, and Andrew G. Barto. Learning Grounded Finite-State Representations from Unstructured Demonstrations . (Freely accessible draft.) The International Journal of Robotics Research 34(2), pages 131-157, February 2015. [Video]

2014
  1. G.D. Konidaris and F. Doshi-Velez. Hidden Parameter Markov Decision Processes: An Emerging Paradigm for Modeling Families of Related Tasks. In Proceedings of the AAAI 2014 Fall Symposium on Knowledge, Skill, and Behavior Transfer in Autonomous Robots, November 2014.

  2. C. Amato, G.D. Konidaris, J.P. How and L.P. Kaelbling. Decentralized Decision-Making Under Uncertainty for Multi-Robot Teams. In Proceedings of the 2014 IROS Workshop on The Future of Multiple-Robot Research and Its Multiple Identities, September 2014.

  3. E.L. Nelson, G.D. Konidaris, and N.E. Berthier. Hand preference status and reach kinematics in infants. Infant Behavior and Development, 37(4), 615-623.

  4. G.D. Konidaris, L. Kaelbling and T. Lozano-Perez. Constructing Symbolic Representations for High-Level Planning. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, pages 1932-1940, July 2014.

  5. N. Hollingsworth, J. Meyer, R. McGee, J. Doering, G.D. Konidaris and L. Kaelbling. Optimizing a Start-Stop Controller using Policy Search. In Proceedings of the Twenty-Sixth Annual Conference on Innovative Applications of Artificial Intelligence, pages 2984-2989, July 2014.

  6. B.C. da Silva, G.D. Konidaris, and A.G. Barto. Active Learning of Parameterized Skills. In Proceedings of the Thirty First International Conference on Machine Learning, pages 1737-1745, June 2014.

  7. B.C. da Silva, G. Baldassarre, G.D. Konidaris, and A.G. Barto. Learning Parameterized Motor Skills on a Humanoid Robot. In Proceedings of the IEEE International Conference on Robotics and Automation, pages 5239-5244, May 2014. [Video]

  8. C. Amato, G.D. Konidaris, G. Cruz, C.A. Maynor, J.P. How and L.P. Kaelbling. Planning for Decentralized Control of Multiple Robots Under Uncertainty. In Proceedings of the 2014 ICAPS Workshop on Planning and Robotics, June 2014. [ArXiv] [Video]

  9. C. Amato, G.D. Konidaris and L.P. Kaelbling. Planning with Macro-Actions in Decentralized POMDPs. In Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems, pages 1273-1280, May 2014.

2013
  1. A.G. Barto, G.D. Konidaris, and C.M. Vigorito. Behavioral Hierarchy: Exploration and Representation. In Computational and Robotic Models of the Hierarchical Organization of Behavior, Baldassarre, Gianluca; Mirolli, Marco (Eds.), pages 13-46, Springer, Berlin, October 2013.

  2. F. Doshi-Velez and G.D. Konidaris. Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations. ArXiV preprint arXiv:1308.3513, August 2013.

  3. C. Trewick, P. Ranchod and G.D. Konidaris. Preferential Targeting of HIV Infected Hubs in a Scale-free Sexual Network. In the Annual Conference of the Computational Social Science Society of the Americas, August 2013. Honorable mention, best paper competition.

  4. G.D. Konidaris. Robots, Skills, and Symbols (Extended Abstract). In Proceedings of the 2013 Workshop on Machine Learning for Interactive Systems, August 2013.

  5. G.D. Konidaris, L.P. Kaelbling and T. Lozano-Perez. Symbol Acquisition for Task-Level Planning. In the AAAI 2013 Workshop on Learning Rich Representations from Low-Level Sensors, July 2013.

    Please note that this paper has been superceded by our AAAI 2014 paper.

  6. G.D. Konidaris, S. Kuindersma, S. Niekum, R.A. Grupen and A.G. Barto. Robot Learning: Some Recent Examples. In Proceedings of the Sixteenth Yale Workshop on Adaptive and Learning Systems, pages 71-76, Center for Systems Science, Dunham Laboratory, Department of Electrical Engineering, Yale University, New Haven CT, June 2013.

  7. G. Goretkin, A. Perez, R. Platt and G.D. Konidaris. Optimal Sampling-Based Planning for Linear-Quadratic Kinodynamic Systems. In Proceedings of the IEEE International Conference on Robotics and Automation, pages 2429-2436, May 2013.

2012
  1. F. Doshi-Velez and G.D. Konidaris. Transfer Learning by Discovering Latent Task Parametrizations. In the NIPS 2012 Workshop on Bayesian Nonparametric Models for Reliable Planning And Decision-Making Under Uncertainty, December 2012.

  2. S. Niekum, S. Osentoski, G.D. Konidaris and A.G. Barto. Learning and Generalization of Complex Tasks from Unstructured Demonstrations. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 5239-5246, October 2012.

  3. B.C. da Silva, G.D. Konidaris and A.G. Barto. Learning Parameterized Skills. In Proceedings of the Twenty Ninth International Conference on Machine Learning, pages 1679-1686, June 2012.

  4. A. Perez, R. Platt, G.D. Konidaris, L.P. Kaelbling and T. Lozano-Perez. LQR-RRT*: Optimal Sampling-Based Motion Planning with Automatically Derived Extension Heuristics. In Proceedings of the IEEE International Conference on Robotics and Automation, pages 2537-2542, May 2012.

  5. G.D. Konidaris, I. Scheidwasser and A.G. Barto. Transfer in Reinforcement Learning via Shared Features. Journal of Machine Learning Research, 13:1333-1371, May 2012.

  6. E.L. Nelson, G.D. Konidaris, N.E. Berthier, M.C. Braun, M.S.F.X. Novak, S.J. Suomi and M.A. Novak. Kinematics of reaching and implications for handedness in rhesus monkey infants. Developmental Psychobiology 54(4), pages 460-467, May 2012.

  7. G.D. Konidaris, S.R. Kuindersma, R.A. Grupen and A.G. Barto. Robot Learning from Demonstration by Constructing Skill Trees. The International Journal of Robotics Research 31(3), pages 360-375, March 2012. (Freely accessible draft.)

2011
  1. G.D. Konidaris, S. Niekum and P.S. Thomas. TDγ: Re-evaluating Complex Backups in Temporal Difference Learning. Advances in Neural Information Processing Systems 24, pages 2402-2410, December 2011.

  2. G.D. Konidaris, S.R. Kuindersma, R.A. Grupen and A.G. Barto. Autonomous Skill Acquisition on a Mobile Manipulator. In Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, pages 1468-1473, August 2011.

  3. G.D. Konidaris, S. Osentoski and P.S. Thomas. Value Function Approximation in Reinforcement Learning using the Fourier Basis. In Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, pages 380-385, August 2011.

    Source code for the Fourier Basis is available on my software page.

  4. G.D. Konidaris, S.R. Kuindersma, R.A. Grupen and A.G. Barto. CST: Constructing Skill Trees by Demonstration. In Proceedings of the ICML Workshop on New Developments in Imitation Learning, July 2011.

  5. G.D. Konidaris, S.R. Kuindersma, R.A. Grupen and A.G. Barto. Acquiring Transferrable Mobile Manipulation Skills. In the RSS 2011 Workshop on Mobile Manipulation: Learning to Manipulate, June 2011.

  6. G.D. Konidaris. Autonomous Robot Skill Acquisition. PhD Thesis, Department of Computer Science, University of Massachusetts Amherst, May 2011.

2010
  1. G.D. Konidaris, S.R. Kuindersma, A.G. Barto and R.A. Grupen. Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories. Advances in Neural Information Processing Systems 23, pages 1162-1170, December 2010.

  2. S.R. Kuindersma, G.D. Konidaris, R.A. Grupen, A.G. Barto. Learning from a Single Demonstration: Motion Planning with Skill Segmentation (poster abstract). NIPS Workshop on Learning and Planning in Batch Time Series Data. December 2010.

2009
  1. G.D. Konidaris and A.G. Barto. Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining. Advances in Neural Information Processing Systems 22, pages 1015-1023, December 2009.

    The code for the Pinball domain is available here. You can also download videos of the solutions shown in the paper.

    An earlier version appeared as: G.D. Konidaris and A.G. Barto. Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining. Technical Report UM-CS-2008-24, Department of Computer Science, University of Massachusetts Amherst, July 2008.

  2. G.D. Konidaris and A.G. Barto. Efficient Skill Learning Using Abstraction Selection. In Proceedings of the Twenty First International Joint Conference on Artificial Intelligence, pages 1107-1112, July 2009.

  3. G.D. Konidaris and A.G. Barto. Towards the Autonomous Acquisition of Robot Skill Hierarchies (poster abstract). In the Robotics: Science and Systems Workshop on Bridging the Gap Between High-Level Discrete Representations and Low-Level Continuous Behaviors, Seattle, June 2009.

  4. G.D. Konidaris and S. Osentoski. Value Function Approximation using the Fourier Basis (extended abstract). In the Multidisciplinary Symposium on Reinforcement Learning, Montreal, Canada, June 2009.

    Please note that this paper has been superceded by our AAAI 2011 paper.

    Source code for the Fourier Basis is available on my software page.

  5. G.D. Konidaris and A.G. Barto. Skill Chaining: Skill Discovery in Continuous Domains (extended abstract). In the Multidisciplinary Symposium on Reinforcement Learning, Montreal, Canada, June 2009.

    The code for the Pinball domain is available here.

2008
  1. G.D. Konidaris and A.G. Barto. Sensorimotor Abstraction Selection for Efficient, Autonomous Robot Skill Acquisition. Proceedings of the 7th IEEE International Conference on Development and Learning, pages 151-156, August 2008.

  2. G.D. Konidaris. Autonomous Robot Skill Acquisition (thesis summary). Doctoral Symposium, 23rd National Conference on Artificial Intelligence (AAAI 2008), July 2008.

  3. G.D. Konidaris and S. Osentoski. Value Function Approximation in Reinforcement Learning using the Fourier Basis. Technical Report UM-CS-2008-19, Department of Computer Science, University of Massachusetts Amherst, June 2008.

    Please note that this paper has been superceded by our AAAI 2011 paper.

    Source code for the Fourier Basis is available on my software page.

  4. E.L. Nelson, G.D. Konidaris and N.E. Berthier. Using Real-Time Motion Capture to Measure Handedness in Infants. Poster presentation at the XVIth Biennial International Conference on Infant Studies, Vancouver, Canada, March 2008.

2007
  1. L. Georgopoulos, G.M. Hayes and G.D. Konidaris. A Forward Model of Optic Flow for Detecting External Forces. Proceedings of the IEEE/RSJ 2007 International Conference on Intelligent Robots and Systems, pages 913-918, October 2007.

  2. G.D. Konidaris and A.G. Barto. Building Portable Options: Skill Transfer in Reinforcement Learning. In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, pages 895-900, January 2007.

    An earlier version appeared as: G.D. Konidaris and A.G. Barto. Building Portable Options: Skill Transfer in Reinforcement Learning. Technical Report UM-CS-2006-17, Department of Computer Science, University of Massachusetts at Amherst, March 2006.

2006
  1. G.D. Konidaris and A.G. Barto. An Adaptive Robot Motivational System. In From Animals to Animats 9: Proceedings of the 9th International Conference on the Simulation of Adaptive Behavior, pages 346-356, September 2006.

  2. G.D. Konidaris. A Framework for Transfer in Reinforcement Learning. In the ICML-06 Workshop on Structural Knowledge Transfer for Machine Learning, Pittsburgh PA, June 2006.

  3. G.D. Konidaris and A.G. Barto. Autonomous Shaping: Knowledge Transfer in Reinforcement Learning. In Proceedings of the Twenty Third International Conference on Machine Learning, pages 489-496, June 2006.

    An earlier version appeared as: G.D. Konidaris and A.G. Barto. Autonomous Shaping: Learning to Predict Reward for Novel States. Technical Report UM-CS-2005-58, Department of Computer Science, University of Massachusetts at Amherst, September 2005.

  4. S. Rauchas, B. Rosman, G.D. Konidaris and I.D. Sanders. Language Performance at High School and Success in First Year Computer Science. In Proceedings of the 37th SIGCSE Technical Symposium on Computer Science Education, pages 398-402, March 2006.

2005
  1. F.J. Stewart, T. Taylor and G.D. Konidaris. METAMorph: Experimenting with Genetic Regulatory Networks for Artificial Development. Proceedings of the VIIIth European Conference on Artificial Life, pages 108-117, September 2005.

  2. A. Stout, G.D Konidaris and A.G. Barto. Intrinsically Motivated Reinforcement Learning: A Promising Framework for Developmental Robot Learning. In The AAAI Spring Symposium on Developmental Robotics, March 2005.

  3. G.D. Konidaris and G.M. Hayes. An Architecture for Behavior-Based Reinforcement Learning. Adaptive Behavior 13(1), pages 5-32, March 2005. (Freely accessible draft.)

2004
  1. G.D. Konidaris and G.M. Hayes. Anticipatory Learning for Focusing Search in Reinforcement Learning Agents, The Second Workshop on Anticipatory Behavior in Adaptive Learning Systems (ABiALS 2004), July 2004.

  2. G.D. Konidaris and G.M. Hayes. Estimating Future Reward in Reinforcement Learning Animats using Associative Learning. In From Animals to Animats 8: Proceedings of the 8th International Conference on the Simulation of Adaptive Behavior, pages 297-304, July 2004.

  3. G.D. Konidaris, T. Taylor and J.C.T Hallam. HydroGen: Automatically Generating Self-Assembly Code for Hydron Units. In Proceedings of The Seventh International Symposium on Distributed Autonomous Robotic Systems, pages 33-42, June 2004.

2003
  1. G.D. Konidaris. Behaviour-Based Reinforcement Learning. Master's Thesis, School of Informatics, University of Edinburgh, 2003.

2002
  1. G.D. Konidaris, D.A. Shell and N. Oren. Evolving Neural Networks to Play the Capture Game. Proceedings of the SAICSIT 2002 Postgraduate Symposium, September 2002.

2001
  1. G.D. Konidaris. Axial Line Placement in Deformed Urban Grids. Honours Dissertation, School of Computer Science, University of the Witwatersrand, 2001.

    Also released as: G.D. Konidaris and I.D. Sanders, Axial Line Placement in Deformed Urban Grids. Technical Report TR-Wits-CS-2002-04, School of Computer Science, University of the Witwatersrand, April 2002.

  2. J. Adler, G.D. Christelis, J.A. Deneys, G.D. Konidaris, G. Lewis, A.G. Lipson, R.L. Phillips, D.K. Scott-Dawkins, D.A. Shell, B.V. Strydom, W.M. Trakman and L.D. Van Gool. Finding Adjacencies in Non-Overlapping Polygons. Electronic Paper, Proceedings of the 2001 SAICSIT Conference, September 2001.