©Thomas Voss

Research Colloquium of Information Systems

08. Apr

In the context of the research colloquium of Information Systems refers Thomas Voss about "DYNAMICALLY CHANGING SEQUENCING RULES WITH REINFORCEMENT LEARNING".

Date and time: 08.04.2021 at 16:15
Location: digital via Zoom (see below)

Abstract:
Generating the best sequence for operations to be processed on a machine can be difficult, especially under uncertain conditions. Applying decentral sequencing rules has been a viable option; however, no rule exists that can outperform all other rules under varying system states. For this reason, Reinforcement Learning (RL) is used to train a human comprehensible and context aware hyper-heuristic. The evaluation shows that the trained agent can dynamically adjust sequencing rules based on the system’s state, thereby matching, and outperforming the presumed best static sequencing rules. Given an unknown system state, the agent’s knowledge is partially transferrable and provides a robust performance.

Join Zoom Meeting
https://leuphana.zoom.us/j/96455201912?pwd=bzBwT3NqL3o2b3RqRGZwL2VwS0RBdz09

Meeting-ID: 964 5520 1912
Identification code: 5ghwu8
Quick dial mobile:
+493056795800,,96455201912#,,,,*170203# Germany
+496938079883,,96455201912#,,,,*170203# Germany

Dialling in according to current location
        +49 30 5679 5800 Germany
        +49 69 3807 9883 Germany
        +49 695 050 2596 Germany
        +49 69 7104 9922 Germany
Meeting-ID: 964 5520 1912
Identification code: 170203
Search area code: https://leuphana.zoom.us/u/aeBWnn4ttw

Join via SIP
96455201912@zoomcrc.com

Join via H.323
162.255.37.11 (USA West)
162.255.36.11 (USA East)
213.19.144.110 (Amsterdam Netherlands)
213.244.140.110 (Germany)
Identification code: 170203
Meeting-ID: 964 5520 1912