Publications and RLPark usages

There are different ways to use RLPark: for running experiments, as an implementation template to copy-paste the code from, for making videos for presentations or teaching, etc.

If you use RLPark in one way or another, I would appreciate if you could let me know about it. Of course, this has nothing mandatory, but this page justifies for my funders the time I spend working on RLPark to make it publicly available. So, please send me an email (thomas.degris@inria.fr) with a reference on your paper, or your name, your institution, and a line about how you used/use RLPark. I will update this page with this information. Thank you.

So far, RLPark usages and publications are:
  • Between instruction and reward: human-prompted switching. P.M. Pilarski and R.S. Sutton (2012) In the AAAI 2012 Fall Symposium on Robots Learning Interactively from Human Teachers, Arlington, VA, USA. Experiments run with RLPark.
  • Exploring artificial intelligence and reinforcement learning. P. Pilarski at TEDx Edmonton 2012. Invited talk. Live demo of RLPark with a Nao robot.
  • Overview: Exploring artificial intelligence and reinforcement learning (video) P. Pilarski (2012) on BreakfastTV, CityTV. Invited talk. Zephyr and RLPark running on television.
  • Off-policy Actor-Critic. T. Degris, M. White, R. S. Sutton (2012) In Proceedings of the 29th International Conference on Machine Learning. Experiments run with RLPark. RLPark Demo.
  • Learning About Sensorimotor Data (video). NIPS Dec 13, 2011 and JNNS Dec 15 2011 R. Sutton, Invited talk. Experiments run with RLPark.
  • Multi-timescale Nexting in a Reinforcement Learning Robot. J. Modayil, A. White, R. S. Sutton (2012). Proceedings of the Conference on the Simulation of Adaptive Behavior. Experiments run with RLPark.
  • Dynamic Switching and Real-time Machine Learning for Improved Human Control of Assistive Biomedical Robots. P. M. Pilarski, M. R. Dawson, T. Degris, J. P. Carey, R. S. Sutton (2012). In Proceedings of the Fourth IEEE International Conference on Biomedical Robotics and Biomechatronics (BioRob). Experiments run with RLPark.
  • Scaling-up Knowledge for a Cognizant Robot. T. Degris, J. Modayil (2012). In notes of the AAAI Spring Symposium on Designing Intelligent Robots: Reintegrating AI. Experiments run with RLPark.
  • Model-Free Reinforcement Learning with Continuous Action in Practice. T. Degris, P. M. Pilarski, R. S. Sutton (2012). In Proceedings of the 2012 American Control Conference. Experiments run with RLPark. RLPark Demo.
  • Tuning-free step-size adaptation. A. R. Mahmood, R. S. Sutton, T. Degris, P. M. Pilarski (2012). In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Data collected with RLPark.
  • Online Human Training of a Myoelectric Prosthesis Controller via Actor-Critic Reinforcement Learning. P. M. Pilarski, M. R. Dawson, T. Degris, F. Fahimi, J. P. Carey, R. S. Sutton (2011). Proceedings of the 2011 IEEE International Conference on Rehabilitation Robotics. Experiments run with RLPark.
  • Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction. R. S. Sutton, J. Modayil, M. Delp, T. Degris, P. M. Pilarski, A. White, D. Precup (2011). In Proceedings of the Tenth International Conference on Autonomous Agents and Multiagent Systems. Experiments run with RLPark.
  • Real-time Machine Learning in Rehabilitation Robotics for Adaptable Artificial Limbs. P.M. Pilarski, M.R. Dawson, T. Degris, F. Fahimi, J. Carey, R.S. Sutton (2011). Glenrose Rehabilitation Hospital Research Symposium (Edmonton, Alberta, Canada). Tech Futures Summit 2011: Deploying Innovation (Banff, Alberta, Canada). Experiments run with RLPark.
  • An Encouraging Mobile Robot in the Glenrose Rehabilitation Hospital. T. Degris, P.M. Pilarski, J. Modayil, R.S. Sutton, M.J. Cimolini, and J. Raso. (2011). 7th International Congress on Industrial and Applied Mathematics, (ICIAM) (Vancouver, British Columbia, Canada). Robot controlled with RLPark.
  • Off-policy knowledge maintenance for robots. J. Modayil, P. M. Pilarski, A. White, T. Degris, R. S. Sutton (2010). Robotics Science and Systems Workshop: Towards Closing the Loop: Active Learning for Robotics. Experiments run with RLPark.
  • Small-Timescale Reinforcement Learning for Power Management on a Mobile Robot. P.M. Pilarski, T. Degris, and R.S. Sutton (2010). Alberta Power Industry Consortium Power and Energy Innovation Forum (Edmonton, Alberta, Canada). Experiments run with RLPark.
  • Continuous Actor-Critic Methods for Adaptive Prosthetics. P.M. Pilarski, M.R. Dawson, T. Degris, F. Fahimi, J. Carey, and R.S. Sutton (2010). In proceedings of the MITACS/CORS Joint Annual Conference (Edmonton, Alberta, Canada). Experiments run with RLPark.
  • Robust Step-size Adaptation for Online Optimization. A. Mahmood, T. Degris, P.M. Pilarski, and R.S. Sutton (2010). In proceedings of the MITACS/CORS Joint Annual Conference (Edmonton, Alberta, Canada). Data collected with RLPark.