filler

The repository contains useful downloadable material related to my research and teaching, including Matlab software, presentations, and demonstration movies. Presentations are selectively chosen for tutorial value. If an item has a "»" button to its right, this button can be clicked to reveal more information; the "«" button then hides this information again (requires Javascript).

Software

  • Approximate RL and DP toolbox, latest snapshot, including bugfixes and new, work-in-progress algorithms and experiments - possibly with their own, new bugs. (9 January 2016, 1.9 MBytes). »
  • Optimistic planning, a selection of algorithms as a stand-alone package. (13 July 2013, 79.3 KBytes). »
  • Approximate RL and DP toolbox, July 2013 release. (13 July 2013, 1.6 MBytes). »
  • MARL toolbox ver. 1.3, a Matlab multi-agent reinforcement learning toolbox (4 August 2010, 336.9 KBytes). »
  • MARL toolbox documentation, the documentation files for the MARL toolbox (4 August 2010, 223.1 KBytes). »
  • Approximate RL and DP toolbox, developed in Matlab. (6 June 2010, 967.6 KBytes). »
  • makepdf, a Windows XP batch script to automate the creation of PDF files from DVI (21 November 2008, 2.4 KBytes).

Presentations

  • Basics of Reinforcement Learning, a very condensed introduction to basic dynamic programming and RL methods. Taught at the Transylvanian Summer School on Machine Learning, in Cluj-Napoca, Romania (20 July 2018, 4.5 MBytes).
  • AI Planning with Applications to Switched Systems, discussing, in addition to some planning techniques, their adaptations for switched system control. Keynote at the IFAC CESCIT conference (6 June 2018, 5.4 MBytes).
  • Online, Optimistic Planning for Markov Decision Processes, an in-depth course mainly on my recent research into optimistic planning algorithms, with a practical session. Taught at the ACAI Summer School on RL, in Nieuwpoort, Belgium (10 October 2017).
  • Approximate Dynamic Programming and Reinforcement Learning for Control, an invited, three-day intensive Master course at the Polytechnic University of Valencia, Spain (21 June 2017). »

Demonstration Movies

  • Fall detection using a quadrotor, A Parrot AR.Drone 2 monitors a person for falls while flying at a set distance and orientation. The location of the person, as well as falls, are detected with deep-learning vision algorithms. With Paul Dragan and Cristi Iuga, see our conference paper for details. (1 December 2017).
  • Assistive robot demo using online POMDP planning, Cyton Gamma 1500 robot arm, with Pioneer3AT mobile base and end-effector camera, flips off electrical switches forgotten on. Uses an online planning algorithm called AEMS2 for partially-observable Markov decision processes. With Elod Pall and Levente Tamas, see our IROS paper for details. (7 July 2016).
  • Planning to swing up a rotary pendulum in real time, using the continuous-action simultaneous optimistic optimization for planning (SOOP) algorithm. With Elod Pall. (24 November 2014).
  • Learning to swing up an inverted pendulum, using online least-squares policy iteration. (8 January 2009, 51.8 MBytes). »
  • Robot goalkeeper learning to catch the ball, using approximate online RL and experience replay (demo by Sander Adam). (1 October 2008, 13.3 MBytes).