RLDM 2017 Schedule
University of Michigan, Ann Arbor, MI

Sunday June 11, 2017 – Tutorials

12:00pm-1:00pm – Registration desk open, Rackham 4th floor
12:00-5:00pm – Refreshments available in the East & West Conference Rooms

Track 1 – Location: Rackham Assembly Hall.  

1:00-2:40pm Basic tutorial, (intro to AI/RL track): Joelle Pineau

Track 2 – Location: Rackham Amphitheatre.  

1:00- 2:40pm Basic tutorial (intro to Bio/psych track): Anne Collins

Session 2 – Location: Rackham Amphitheatre.  

2:45-4:10 Advanced tutorial, John Schulman: “Deep Reinforcement Learning Through Policy Optimization”
4:30-6:00 Advanced tutorial, Matthew Botvinick: “Deep RL, fast and slow”

6:00pm-12:00am Private tent, bar and activities at Ann Arbor Summer Festival’s “Top of the Park”

Monday June 12, 2017

7:30-noon  Registration desk open in Rackham Lobby

7:30-8:30am Breakfast, Rackham Lobby

Session 1 – (8:30-10:30am) Rackham Auditorium

8:30-9:10am Yael Niv: “Learning State Representations”
9:10-9:30am Arkady Konovalov; Ian Krajbich: “Neurocomputational Dynamics of Sequence Learning”
9:30-9:50 am Wen Sun; Arun Venkatraman; Byron Boots; Geoff Gordon; J. Andrew Bagnell: “Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction”
9:50-10:30am Anca Dragan: “Humans Make for Complicated Transition Models”

10:30-11:00am coffee break, Rackham Lobby

Session 2 – (11am-12:20pm) Rackham Auditorium

11:00-11:40 am Uma Karmarkar: “Choosing without knowing: biased information processing in ambiguous decision-making”
11:40-12:00 pm Asma Motiwala; Sofia Soares; Bassam Atallah; Joseph Paton; Christian Machens: “Variability in judgement of time is reflected in reward prediction errors and dopaminergic activity”
12-12:20 pm Michael C Mozer; Shruthi Sukumar; Shabnam Hakimi; Camden Elliott-Williams; Adrian Ward: “Overcoming Temptation: Incentive Design for Intertemporal Choice”

12:45-2:00pm special RSVP event: Networking Lunch, Michigan League building, Michigan Room, 2nd floor; others: lunch on your own

Session 3 (2:30-4:30) Rackham Auditorium

2:30-3:10pm Jon How: “Planning under Uncertainty: Theory and Practice”
3:10-3:30pm Gautham Vasan; Patrick M. Pilarski: “Mirrored Bilateral Training of a Myoelectric Prosthesis with a Non-Amputated Arm via Actor-Critic Reinforcement Learning”
3:30-3:50pm Angela Radulescu; Yuan Chang Leong; Yael Niv: “Reward-sensitive attention dynamics during human reinforcement learning”
3:50-4:10pm Sean McGregor; Rachel Houtman; Ronald Metoyer; Claire Montgomery; Thomas Dietterich:  “Visualizing High-Dimensional MDPs with Model-Free Monte Carlo”
4:10-4:30pm Anirudha Majumdar; Sumeet Singh; Marco Pavone: “Risk-sensitive Inverse Reinforcement Learning via Coherent Risk Models”

Spotlights Session 1 (4:30-4:40pm) – Rackham Auditorium

  1. Jaden B Travnik; Patrick M. Pilarski: “Effective, Time-Efficient State Representations for Human-Machine Decision Making”
  2. Melissa J. Sharpe; Chun Yun Chang; Melissa A. Liu; Hannah M. Batchelor; Lauren E. Mueller; Joshua L. Jones; Yael Niv; Geoffrey Schoenbaum: “Dopamine transients are sufficient and necessary for acquisition of model-based associations.”
  3. David Abel; Emily Reif; Michael Littman: “Improving Solar Panel Efficiency Using Reinforcement Learning”
  4. Siyu Wang; Robert Wilson: “What is the nature of decision noise in random exploration?”
  5. Pierre-Luc Bacon; Doina Precup: “Unifying Multi-Step Methods through Matrix Splitting”

4:40-7:40 pm Poster Session 1, refreshments & snacks (posters available until tbd). Rackham 4th floor. RLDM2017 Monday Poster List

7:40pm Banquet, Michigan League Ballroom
               Speaker: Margaret Boden

Tuesday June 13, 2017

7:30-8:30am Breakfast, Rackham Lobby

Session 4 (8:30-10:30am) Rackham Auditorium

8:30-9:10am Michael Frank: “Chunking as an adaptively learned strategy for lossy data compression in working memory”
9:10-9:30am Erik Talvitie: “Self-Correcting Models for Model-Based Reinforcement Learning”
9:30-9:50am Adam Morris; Fiery Cushman: “Can habits be explained without model-free RL?”
9:50-10:10am Chao Qin; Diego Klabjan; Daniel Russo: “Improving the Expected Improvement Algorithm”
10:10-10:30am Paul M Krueger; Falk Lieder; Tom Griffiths: “Enhancing metacognitive reinforcement learning using reward structures and feedback”

10:30-11:00am coffee/tea break, Rackham Lobby

Session 5 (11:00am-12:20pm) Rackham Auditorium

11:00-11:20am Marlos C. Machado; Marc G. Bellemare; Michael Bowling: “A Laplacian Framework for Option Discovery in Reinforcement Learning”
11:20-11:40pm Kevin Lloyd; Peter Dayan: “Interrupting Options: Minimizing Decision Costs via Temporal Commitment and Low-Level Interrupt”
11:40-12:20pm Sam Gershman: “Using Video Games to Reverse Engineer Human Intelligence”

12:45-2:00pm Special RSVP event: Career mentoring lunch for trainees- Michigan League building, Michigan Room, 2nd floor; others: lunch on your own

Session 6 (2:30-4:30pm) Rackham Auditorium

2:30-3:10pm Jan Peters: “Reinforcement Learning of Robot Skills: From Policy Gradients to
Divergence-based Policy Search”
3:10-3:30pm Ross Otto; Johannes Eichstaedt: “The Interplay between Prediction Errors, Twitter Mood, and Real-World Gambling”
3:30-3:50pm Max Kleiman-Weiner; Mark Ho; Joseph Austerweil; Michael Littman; Joshua Tenenbaum: “Learning to Cooperate and Compete”
3:50-4:30pm Ece Kamar: “Directions in Hybrid Intelligence: Complementing AI Systems with Human Intelligence”

Spotlights Session 2 (4:30-4:40pm) – Rackham Auditorium

  1. Harrison Ritz; Matt Nassar; Michael Frank; Amitai Shenhav: “A PID model of feedback-controlled decision-making in dynamic environments”
  2. Herke van Hoof; Jan Peters: “Generalized Exploration in Policy Search”
  3. Michael Pereira; Christian K. Machens; Rui M. Costa; Thomas Akam: “A novel navigation task for studying route planning in rodents”
  4. Niranjani Prasad; Li-Fang Cheng; Corey Chivers; Michael Draugelis; Barbara E. Engelhardt: “A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units”
  5. Vanessa M Brown; Jacob Lee; Brooks King-Casas; Pearl H Chiu: “Training Reinforcement Learning”

4:40-7:40pm Poster Session 2, refreshments & snacks (posters available until tbd). Rackham 4th floor. RLDM2017 Tuesday Poster List

Wednesday June 14, 2017

7:30-8:30am – Breakfast, Rackham Lobby

Session 7 (8:30-10:30am) Rackham Auditorium

8:30-9:10am Volodymyr Mnih: “Faster and More Data-Efficient Deep Reinforcement Learning”
9:10-9:50am Leah Somerville: “Neurodevelopment and adolescent motivation x control interactions” 
9:50-10:30am Elizabeth Phelps: “Mechanisms of Threat Control in Humans”

10:30-11:00am coffee/tea break, Rackham Lobby

Session 8 (11:00am-1:00pm) Rackham Auditorium

11:00-11:40am Lihong Li: “Deep Reinforcement Learning for Conversational Systems”
11:40-12:20pm Kent Berridge: “Desire Beyond Reinforcement Learning”
12:20-1:00pm Ron Parr: “Understanding Features in Reinforcement Learning”