Hierarchical Robot Learning and Planning

Compsci 590.2 Fall 2014

Instructor: George Konidaris (gdk at cs dot duke dot edu)
Location: North Building 311

Please note that the first meeting of the class is on September 2nd, the class will not meet August 25th-29th.

September 2nd Reinforcement Learning in Robotics: A Survey. Kober, Bagnell and Peters, IJRR 2013.
September 4th (same as above)
September 9th Policy Gradient Reinforcement Learning for Fast Quadrupedal Locomotion. Kohl and Stone, ICRA 2004.
Path Integral Policy Improvement with Covariance Matrix Adaptation. Stulp and Sigaud, ICML 2012.
September 11th PILCO: A Model-Based and Data-Efficient Approach to Policy Search. Deisenroth and Rasmussen, ICML 2011.
September 16th No class
September 18th No class
September 23rd Learning Parameterized Skills, da Silva, Konidaris, and Barto, ICML 2012.
September 25th Learning to select and generalize striking movements in robot table tennis, Mulling, Kober, Kroemer, and Peters, IJRR 2013.
September 30th Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning, Sutton, Precup, and Singh, AIJ 1999.
October 2nd Skill characterization based on betweenness, Simsek and Barto, NIPS 2008.
Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining. Konidaris and Barto, NIPS 2009.
October 7th Autonomous Skill Acquisition on a Mobile Manipulator. Konidaris, Kuindersma, Grupen and Barto, AAAI 2011.
October 9th Incremental Semantically Grounded Learning from Demonstration. Niekum, Chitta, Marthi, Osentoski, and Barto. RSS 2013.
October 14th No class (Fall break)
October 16th Advanced Introduction to Planning: Models and Methods, IJCAI 2011 Tutorial, Hector Geffner.
A Brief Overview of AI Planning, Jussi Rintanen.
October 21st Constructing Symbolic Representations for High-Level Planning, Konidaris, Kaelbling, and Lozano-Perez, AAAI 2014.
October 23rd No class
October 28th Building abstraction hierarchies (unpublished).
October 30th Robot Motion Planning (slides), Burgard, Stachniss, Bennewitz, and Arras (first 64 slides)
November 4th Sampling-based Algorithms for Optimal Motion Planning, Karaman and Frazzoli. IJRR 2012
November 6th CHOMP: Covariant Hamiltonian Optimization for Motion Planning, Zucker, Ratliff, Dragan, Pivtoraiko, Klingensmith, Dellin, Bagnell, and Srinivasa. IJRR 2012.
STOMP: Stochastic Trajectory Optimization for Motion Planning, Kalakrishnan, Chitta, Theodorou, Pastor and Schaal. ICRA 2011.
November 11th A Hierarchical Approach to Manipulation with Diverse Actions, Barry, Kaelbling and Lozano-Perez, ICRA 2013.
November 13th No class
November 18th Guest Lecture: Kris Hauser.
November 20th Hierarchical Task and Motion Planning in the Now, Kaelbling and Lozano-Perez, ICRA 2011.
November 25th No class (Thanksgiving)
November 27th No class (Thanksgiving)

Please submit your coursework assignments by Friday, December 12th.