Thomas Gabel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Thomas Gabel has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
Martin Riedmiller
Machine Learning Laboratory, Department of Computer Science , Albert-Ludwigs-Universität Freiburg , Germany
1 shared publication- Martin Riedmiller
Machine Learning Lab, Department of Computer Science, Faculty of Engineering, Albert-Ludwigs-University Freiburg, Freiburg, Germany
1 shared publication - Sascha Lange
Albert-Ludwigs-Universtität Freiburg
1 shared publication
Latest Publications
- 13 June 2011
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 50 (1) , 41-61
Distributed policy search reinforcement learning for job-shop scheduling tasks
We interpret job-shop scheduling problems as sequential decision problems that are handled by independent learning agents. These agents act completely decoupled from one another and employ probabilistic dispatching policies for which we propose a compact representation using a small set of real-valued parameters. During ongoing learning, the agents adapt these parameters using policy gradient reinforcement learning, with the aim of improving the performance of the joint policy measured in terms of a standard scheduling objective function. Moreover, we suggest a lightweight communication mechanism that enhances the agents' capabilities beyond purely reactive job dispatching. We evaluate the effectiveness of our learning approach using various deterministic as well as stochastic job-shop scheduling benchmark problems, demonstrating that the utilisation of policy gradient methods can be effective and beneficial for scheduling problems.
- 13 June 2011
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 50 (1) , 41-61
Distributed policy search reinforcement learning for job-shop scheduling tasks
We interpret job-shop scheduling problems as sequential decision problems that are handled by independent learning agents. These agents act completely decoupled from one another and employ probabilistic dispatching policies for which we propose a compact representation using a small set of real-valued parameters. During ongoing learning, the agents adapt these parameters using policy gradient reinforcement learning, with the aim of improving the performance of the joint policy measured in terms of a standard scheduling objective function. Moreover, we suggest a lightweight communication mechanism that enhances the agents' capabilities beyond purely reactive job dispatching. We evaluate the effectiveness of our learning approach using various deterministic as well as stochastic job-shop scheduling benchmark problems, demonstrating that the utilisation of policy gradient methods can be effective and beneficial for scheduling problems.