Click here for my Google Scholar profile.

2016

  • D. J.~Mankowitz, T. A.~Mann, and S. Mannor, “Adaptive skills, adaptive partitions,” in Advances in neural information processing systems 29, 2016, pp. 1588-1596.
    [Bibtex]
    @InProceedings{Mankowitz2016,
    author = {Daniel J.~Mankowitz and Timothy A.~Mann and Shie Mannor},
    title = {Adaptive Skills, Adaptive Partitions},
    booktitle = {Advances in Neural Information Processing Systems 29},
    year = {2016},
    pages = {1588--1596},
    url = {http://papers.nips.cc/paper/6350-adaptive-skills-adaptive-partitions-asap.pdf},
    }
  • T. A. Mann, H. Penedones, S. Mannor, and T. Hester, “Adaptive lambda least-squares temporal difference learning,” arXiv:1612.09465 2016.
    [Bibtex]
    @TechReport{Mann2016,
    author = {Timothy A. Mann and Hugo Penedones and Shie Mannor and Todd Hester},
    title = {Adaptive Lambda Least-Squares Temporal Difference Learning},
    institution = {arXiv:1612.09465},
    year = {2016},
    url = {https://arxiv.org/abs/1612.09465},
    }

2015

  • A. Hallak, F. Schnitzler, T. A. Mann, and S. Mannor, “Off-policy model-based learning under unknown factored dynamics,” in Proceedings of the 32^nd international conference on machine learning, 2015.
    [Bibtex]
    @InProceedings{Hallak2015,
    Title = {Off-policy Model-based Learning under Unknown Factored Dynamics},
    Author = {Assaf Hallak and Francois Schnitzler and Timothy A. Mann and Shie Mannor},
    Booktitle = {Proceedings of the 32^nd International Conference on Machine Learning},
    Year = {2015},
    Owner = {tim},
    Timestamp = {2015.05.19}
    }
  • N. Levin, T. A. Mann, and S. Mannor, “Actively learning to attract followers on twitter,” in Second multidisciplinary conference on reinforcement learning and decision making, 2015.
    [Bibtex]
    @InProceedings{Levin2015,
    Title = {Actively Learning to Attract Followers on Twitter},
    Author = {Nir Levin and Timothy A. Mann and Shie Mannor},
    Booktitle = {Second Multidisciplinary Conference on Reinforcement Learning and Decision Making},
    Year = {2015},
    Owner = {tim},
    Timestamp = {2015.04.12}
    }
  • D. J. Mankowitz, T. A. Mann, and S. Mannor, “Bootstrapping skills,” in Second multidisciplinary conference on reinforcement learning and decision making, 2015.
    [Bibtex]
    @InProceedings{Mankowitz2015,
    Title = {Bootstrapping Skills},
    Author = {Daniel J. Mankowitz and Timothy A. Mann and Shie Mannor},
    Booktitle = {Second Multidisciplinary Conference on Reinforcement Learning and Decision Making},
    Year = {2015},
    Owner = {tim},
    Timestamp = {2015.04.12}
    }
  • T. A. Mann, D. J. Mankowitz, and S. Mannor, “Learning when to switch between skills in a high dimensional domain,” in AAAI-2015 workshop on learning for general competency in video games, 2015.
    [Bibtex]
    @InProceedings{Mann2015a,
    Title = {Learning when to Switch between Skills in a High Dimensional Domain},
    Author = {Timothy A. Mann and Daniel J. Mankowitz and Shie Mannor},
    Booktitle = {{AAAI}-2015 Workshop on Learning for General Competency in Video Games},
    Year = {2015},
    Owner = {tim},
    Timestamp = {2015.02.26}
    }
  • T. A. Mann, D. Precup, and S. Mannor, “Approximate value iteration with temporally extended actions,” Journal of artificial intelligence research, 2015.
    [Bibtex]
    @Article{Mann2015b,
    author = {Timothy A. Mann and Doina Precup and Shie Mannor},
    title = {Approximate Value Iteration with Temporally Extended Actions},
    journal = {Journal of Artificial Intelligence Research},
    year = {2015},
    owner = {tim},
    timestamp = {2015.05.19},
    url = {http://jair.org/media/4676/live-4676-8760-jair.pdf},
    }

2014

  • O. Maillard, T. A. Mann, and S. Mannor, ““How hard is my MDP?” The distribution-norm to the rescue,” in Advances in neural information processing systems 27, 2014.
    [Bibtex]
    @InProceedings{Maillard2014,
    Title = {``{H}ow hard is my {MDP}?'' {T}he distribution-norm to the rescue},
    Author = {Odalric-Ambrym Maillard and Timothy A. Mann and Shie Mannor},
    Booktitle = {Advances in Neural Information Processing Systems 27},
    Year = {2014},
    Owner = {timotyman},
    Timestamp = {2014.09.09}
    }
  • D. J. Mankowitz, T. A. Mann, and S. Mannor, “Time-regularized interrupting options,” in Proceedings of the 31^st international conference on machine learning, 2014.
    [Bibtex]
    @InProceedings{Mankowitz2014,
    Title = {Time-Regularized Interrupting Options},
    Author = {Daniel J. Mankowitz and Timothy A. Mann and Shie Mannor},
    Booktitle = {Proceedings of the 31^{st} International Conference on Machine Learning},
    Year = {2014},
    Owner = {tim},
    Timestamp = {2014.04.12},
    Url = {http://jmlr.org/proceedings/papers/v32/mannb14.html}
    }
  • T. A. Mann and S. Mannor, “Scaling up approximate value iteration with options: better policies with fewer iterations,” in Proceedings of the 31^st international conference on machine learning, 2014.
    [Bibtex]
    @InProceedings{Mann2014a,
    Title = {Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations},
    Author = {Timothy A. Mann and Shie Mannor},
    Booktitle = {Proceedings of the 31^{st} International Conference on Machine Learning},
    Year = {2014},
    Abstract = {We show how options, a class of control structures encompassing primitive and temporally extended actions, can play a valuable role in planning in MDPs with continuous state-spaces. Analyzing the convergence rate of Approximate Value Iteration with options reveals that for pessimistic initial value function estimates, options can speed up convergence compared to planning with only primitive actions even when the temporally extended actions are suboptimal and sparsely scattered throughout the state-space. Our experimental results in an optimal replacement task and a complex inventory management task demonstrate the potential for options to speed up convergence in practice. We show that options induce faster convergence to the optimal value function, which implies deriving better policies with fewer iterations.},
    Owner = {tim},
    Timestamp = {2014.01.01},
    Url = {http://jmlr.org/proceedings/papers/v32/mann14.html}
    }
  • T. A. Mann, D. Precup, and S. Mannor, “Fast mdp planning with landmarks,” in NIPS 2014 Workshop on Large-scale reinforcement learning and Markov decision problems, 2014.
    [Bibtex]
    @InProceedings{Mann2014,
    Title = {Fast MDP planning with landmarks},
    Author = {Timothy A. Mann and Doina Precup and Shie Mannor},
    Booktitle = {{NIPS 2014 Workshop on Large-scale reinforcement learning and Markov decision problems}},
    Year = {2014},
    Owner = {timotyman},
    Timestamp = {2014.10.30}
    }

2013

  • T. A. Mann and S. Mannor, “Theoretical analysis of planning with options,” in The 11th european workshop on reinforcement learning (EWRL), 2013.
    [Bibtex]
    @InProceedings{Mann2013a,
    Title = {Theoretical Analysis of Planning with Options},
    Author = {Timothy A. Mann and Shie Mannor},
    Booktitle = {The 11th European Workshop on Reinforcement Learning ({EWRL})},
    Year = {2013},
    Owner = {timotyman},
    Timestamp = {2013.07.15}
    }
  • T. A. Mann and S. Mannor, “The advantage of planning with options,” in Proceedings of the first annual conference on reinforcement learning and decision making (RLDM), 2013.
    [Bibtex]
    @InProceedings{Mann2013b,
    Title = {The Advantage of Planning with Options},
    Author = {Timothy A. Mann and Shie Mannor},
    Booktitle = {Proceedings of the First Annual Conference on Reinforcement Learning and Decision Making ({RLDM})},
    Year = {2013},
    Owner = {timotyman},
    Timestamp = {2013.07.16}
    }
  • [DOI] T. A. Mann, Y. Park, S. Jeong, M. Lee, and Y. Choe, “Autonomous and interactive improvement of binocular visual depth estimation through sensorimotor interaction,” IEEE transactions on autonomous mental development, vol. 5, iss. 1, pp. 74-84, 2013.
    [Bibtex]
    @Article{Mann2013c,
    Title = {Autonomous and Interactive Improvement of Binocular Visual Depth Estimation through Sensorimotor Interaction},
    Author = {Timothy A. Mann and Yunjung Park and Sungmoon Jeong and Minho Lee and Yoonsuck Choe},
    Journal = {{IEEE} Transactions on Autonomous Mental Development},
    Year = {2013},
    Number = {1},
    Pages = {74-84},
    Volume = {5},
    Abstract = {We investigate how a humanoid robot with a randomly initialized binocular vision system can learn to improve judgments about egocentric distances using limited action and interaction that might be available to human infants. First, we show how distance estimation can be improved autonomously. We consider our approach to be autonomous because the robot learns to accurately estimate distance without a human teacher providing the distances to training targets. We find that actions that, in principle, do not alter the robot's distance to the target are a powerful tool for exposing estimation errors. These errors can be used to train a distance estimator. Furthermore, the simple action used (i.e., neck rotation) does not require high level cognitive processing or fine motor skill. Next, we investigate how interaction with humans can further improve visual distance estimates. We find that human interaction can improve distance estimates for far targets outside of the robot's peripersonal space. This is accomplished by extending our autonomous approach above to integrate additional information provided by a human. Together these experiments suggest that both action and interaction are important tools for improving perceptual estimates.},
    Doi = {10.1109/TAMD.2012.2216524},
    ISSN = {1943-0604},
    Keywords = {distance measurement;estimation theory;human-robot interaction;humanoid robots;mobile robots;robot vision;binocular visual depth estimation;distance estimation;egocentric distance;estimation error;human infant;human interaction;humanoid robot;judgment;perceptual estimates;randomly initialized binocular vision system;robot distance;robot peripersonal space;sensorimotor interaction;visual distance estimates;Cameras;Estimation;Feature extraction;Humans;Robot vision systems;Visualization;Action;autonomy;depth estimation;learning;perception;vision},
    Owner = {tim},
    Timestamp = {2013.11.16}
    }

2012

  • Y. Choe and T. A. Mann, “From problem solving to problem posing,” in Brain mind magazine, 2012, pp. 7-8.
    [Bibtex]
    @InProceedings{Choe2012,
    Title = {From problem solving to problem posing},
    Author = {Yoonsuck Choe and Timothy A. Mann},
    Booktitle = {Brain Mind Magazine},
    Year = {2012},
    Pages = {7--8},
    Volume = {1},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }
  • S. Jeong, Y. Park, M. Lee, T. A. Mann, and Y. Choe, “Proactive learning mechanism of sensory perception and behavior generation for an autonomous robot,” in Proceedings of the international conference on brain-mind, 2012.
    [Bibtex]
    @InProceedings{Jeong2012,
    Title = {Proactive learning mechanism of sensory perception and behavior generation for an autonomous robot},
    Author = {Sungmoon Jeong and Yunjung Park and Minho Lee and Timothy A. Mann and Yoonsuck Choe},
    Booktitle = {Proceedings of the International Conference on Brain-Mind},
    Year = {2012},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }
  • T. A. Mann and Y. Choe, “Directed exploration in reinforcement learning with transferred knowledge,” JMLR workshop and conference proceedings: EWRL, vol. 24, pp. 59-76, 2012.
    [Bibtex]
    @Article{Mann2012,
    Title = {Directed Exploration in Reinforcement Learning with Transferred Knowledge},
    Author = {Timothy A. Mann and Yoonsuck Choe},
    Journal = {{JMLR} Workshop and Conference Proceedings: {EWRL}},
    Year = {2012},
    Pages = {59--76},
    Volume = {24},
    Abstract = {Experimental results suggest that transfer learning (TL), compared to learning from scratch, can decrease exploration by reinforcement learning (RL) algorithms. Most existing TL algorithms for RL are heuristic and may result in worse performance than learning from scratch (i.e., negative transfer). We introduce a theoretically grounded and flexible approach that transfers action-values via an intertask mapping and, based on those, explores the target task systematically. We characterize positive transfer as (1) decreasing sample complexity in the target task compared to the sample complexity of the base RL algorithm (without transferred action-values) and (2) guaranteeing that the algorithm converges to a near-optimal policy (i.e., negligible optimality loss). The sample complexity of our approach is no worse than the base algorithm’s, and our analysis reveals that positive transfer can occur even with highly inaccurate and partial intertask mappings. Finally, we empirically test directed exploration with transfer in a multijoint reaching task, which highlights the value of our analysis and the robustness of our approach under imperfect conditions.},
    Owner = {timotyman},
    Timestamp = {2013.03.17}
    }

2011

  • J. R. Chung, J. Kwon, T. A. Mann, and Y. Choe, “Evolution of time in neural networks: from the present to the past, and forward to the future.,” in The relevance of the time domain to neural network models., Springer, 2011.
    [Bibtex]
    @InCollection{Chung2011,
    Title = {Evolution of time in neural networks: From the present to the past, and forward to the future.},
    Author = {Ji Ryang Chung and Jaerock Kwon and Timothy A. Mann and Yoonsuck Choe},
    Booktitle = {The Relevance of the Time Domain to Neural Network Models.},
    Publisher = {Springer},
    Year = {2011},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }
  • T. A. Mann and Y. Choe, “Scaling up reinforcement learning through targeted exploration,” in Proceedings of the 25th AAAI conference on artificial intelligence, 2011, pp. 435-440.
    [Bibtex]
    @InProceedings{Mann2011,
    Title = {Scaling up reinforcement learning through targeted exploration},
    Author = {Timothy A. Mann and Choe, Yoonsuck},
    Booktitle = {Proceedings of the 25th {AAAI} Conference on Artificial Intelligence},
    Year = {2011},
    Pages = {435--440},
    Owner = {tim},
    Timestamp = {2013.11.16}
    }
  • T. A. Mann, Y. Park, S. Jeong, M. Lee, and Y. Choe, “Autonomously improving binocular depth estimation,” in Proceedings of the japanese neural networks society, 2011.
    [Bibtex]
    @InProceedings{Mann2011a,
    Title = {Autonomously improving binocular depth estimation},
    Author = {Timothy A. Mann and Yunjung Park and Sungmoon Jeong and Minho Lee and Yoonsuck Choe},
    Booktitle = {Proceedings of the Japanese Neural Networks Society},
    Year = {2011},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }

2010

  • T. A. Mann and Y. Choe, “Grounding the meaning of nonprototypical smiles on motor behavior,” Behavioral and brain sciences, vol. 33, pp. 453-454, 2010.
    [Bibtex]
    @Article{Mann2010,
    Title = {Grounding the meaning of nonprototypical smiles on motor behavior},
    Author = {Timothy A. Mann and Yoonsuck Choe},
    Journal = {Behavioral and Brain Sciences},
    Year = {2010},
    Pages = {453--454},
    Volume = {33},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }
  • T. A. Mann and Y. Choe, “Prenatal to postnatal transfer of motor skills through motor-compatible sensory representations,” in Proceedings of the nineth international conference on development & learning, 2010.
    [Bibtex]
    @InProceedings{Mann2010a,
    Title = {Prenatal to postnatal transfer of motor skills through motor-compatible sensory representations},
    Author = {Timothy A. Mann and Yoonsuck Choe},
    Booktitle = {Proceedings of the Nineth International Conference on Development \& Learning},
    Year = {2010},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }
  • T. A. Mann and Y. Choe, “Neural conduction delay forces the emergence of predictive function in simulated evolution: function in simulation evolution,” Bmc neuroscience, vol. 11, p. 62, 2010.
    [Bibtex]
    @Article{Mann2010b,
    Title = {Neural Conduction Delay Forces the Emergence of Predictive Function in Simulated Evolution: Function in Simulation Evolution},
    Author = {Timothy A. Mann and Yoonsuck Choe},
    Journal = {BMC Neuroscience},
    Year = {2010},
    Pages = {62},
    Volume = {11},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }

2009

  • M. van Zomeren, J. Peschel, T. A. Mann, G. Knezek, J. Doebbler, J. Davis, T. A. Hammond, A. H. J. Oomes, and R. R. Murphy, “Human-robot interaction observations from a proto-study using uavs for structural inspection,” in Hri ’09: proceedings of the $4^{th}$ ACM/IEEE international conference on human robot interaction, 2009, pp. 235-236.
    [Bibtex]
    @InProceedings{Zomeren2009,
    Title = {Human-Robot Interaction Observations from a Proto-Study Using UAVs for Structural Inspection},
    Author = {Maarten van Zomeren and Joshua Peschel and Timothy A. Mann and Gabe Knezek and James Doebbler and Jeremy Davis and Tracy A. Hammond and Augustinus H. J. Oomes and Robin R. Murphy},
    Booktitle = {HRI '09: Proceedings of the $4^{th}$ {ACM/IEEE} International Conference on Human Robot Interaction},
    Year = {2009},
    Pages = {235--236},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }

2008

  • B. S. Jang, T. A. Mann, and Y. Choe, “Effects of varying the delay distribution in random, scale-free, and small-world networks,” in Proceedings of the 2008 IEEE international conference on granular computing, 2008.
    [Bibtex]
    @InProceedings{Jang2008,
    Title = {Effects of varying the delay distribution in random, scale-free, and small-world networks},
    Author = {Bum Soon Jang and Timothy A. Mann and Yoonsuck Choe},
    Booktitle = {Proceedings of the 2008 {IEEE} International Conference on Granular Computing},
    Year = {2008},
    Owner = {tim},
    Timestamp = {2013.11.17}
    }