Evaluation of physical damage associated with action selection strategies in reinforcement learning

Ivan Koryakovskiy, Heike Vallery, Robert Babuška, Wouter Caarls

Research output: Contribution to journalConference articleScientificpeer-review

5 Citations (Scopus)
54 Downloads (Pure)


Reinforcement learning techniques enable robots to deal with their own dynamics and with unknown environments without using explicit models or preprogrammed behaviors. However, reinforcement learning relies on intrinsically risky exploration, which is often damaging for physical systems. In the case of the bipedal walking robot Leo, which is studied in this paper, two sources of damage can be identified: fatigue of gearboxes due to backlash re-engagements, and the overall system damage due to falls of the robot. We investigate several exploration techniques and compare them in terms of gearbox fatigue, cumulative number of falls and undiscounted return. The results show that exploration with the Ornstein-Uhlenbeck (OU) process noise leads to the highest return, but at the same time it causes the largest number of falls. The Previous Action-Dependent Action (PADA) method results in drastically reduced fatigue, but also a large number of falls. The results reveal a previously unknown trade-off between the two sources of damage. Inspired by the OU and PADA methods, we propose four new action-selection methods in a systematic way. One of the proposed methods with a time-correlated noise outperforms the well-known e-greedy method in all three benchmarks. We provide guidance towards the choice of exploration strategy for reinforcement learning applications on real physical systems.

Original languageEnglish
Pages (from-to)6928-6933
Issue number1
Publication statusPublished - 2017
Event20th World Congress of the International Federation of Automatic Control (IFAC), 2017 - Toulouse, France
Duration: 9 Jul 201714 Jul 2017
Conference number: 20


  • Adaptation
  • Analysis of reliability
  • Autonomous robotic systems
  • diagnosis
  • Fault detection
  • learning in physical agents
  • Reinforcement learning control
  • safety


Dive into the research topics of 'Evaluation of physical damage associated with action selection strategies in reinforcement learning'. Together they form a unique fingerprint.

Cite this