ERLARS 2009 - 2nd International Workshop on
Evolutionary and Reinforcement Learning for Autonomous Robot Systems

This is the programme for the ERLARS 2009 workshop in St Louis, USA. ERLARS 2009 is workshop "Thursday-03" (Th03) at the IROS 2009 conference. The workshop venue is room Mills 3. Please follow the local signs or ask a member of the conference staff for details.

09.00-09:15	Opening
09.15-10:00	Invited Talk: Derandomized Self-Adaptation in Evolutionary Reinforcement Learning by Verena Heidrich-Meisner
10:00-10:30	Coffee break
10:30-11:00	Compiling Neural Networks for Fast Neuro-Evolution by Nils T Siebel, Andreas Jordt and Gerald Sommer
11:00-11:30	Combination of Reinforcement Learning and Neural Networks by Anastasia Noglik and Josef Pauli
11:30-12:00	Using Joint Probability Densities for Simultaneous Learning of Forward and Inverse Models by Mark Edgington, Yohannes Kassahun and Frank Kirchner
12:00-14:00	Lunch break
14.00-14:45	Invited Talk: Uncertain Constraints in Imitation and Reinforcement Learning by Matthew Howard
14:45-15:15	Combining Central Pattern Generators with the Electromagnetism-like Algorithm for Head Motion Stabilization during Quadruped Robot Locomotion by Cristina P Santos, Miguel Oliveira, Vitor Matos, Ana Maria A C Rocha and Lino Costa
15:15-16:00	Coffee break
16:00-16:30	Path Planning for a Mobile Robot Using Self Tuning Fuzzy Logic Controller by Iraj Hassanzadeh and Sevil M Sadigh
16:00-17:00	Discussion on the subject What can a robot system learn by itself, and what is the best way of doing it? This is an open forum to exchange ideas and viewpoints on robot learning. We are looking forward to hearing your opinion on this subject!