Skip to Main content Skip to Navigation
Conference papers

"I'm sorry Dave, I'm afraid I can't do that" Deep Q-Learning From Forbidden Actions

Mathieu Seurin 1, 2, 3, 4 Philippe Preux 3, 4 Olivier Pietquin 5 
3 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
4 Scool - Scool
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : The use of Reinforcement Learning (RL) is still restricted to simulation or to enhance human-operated systems through recommendations. Real-world environments (e.g. industrial robots or power grids) are generally designed with safety constraints in mind implemented in the shape of valid actions masks or contingency controllers. For example, the range of motion and the angles of the motors of a robot can be limited to physical boundaries. Violating constraints thus results in rejected actions or entering in a safe mode driven by an external controller, making RL agents incapable of learning from their mistakes. In this paper, we propose a simple modification of a state-of-the-art deep RL algorithm (DQN), enabling learning from forbidden actions. To do so, the standard Q-learning update is enhanced with an extra safety loss inspired by structured classification. We empirically show that it reduces the number of hit constraints during the learning phase and accelerates convergence to near-optimal policies compared to using standard DQN. Experiments are done on a Visual Grid World Environment and Text-World domain.
Complete list of metadata

https://hal.inria.fr/hal-02387419
Contributor : Mathieu Seurin Connect in order to contact the contributor
Submitted on : Thursday, January 28, 2021 - 10:53:19 AM
Last modification on : Thursday, March 24, 2022 - 3:42:53 AM

File

Dave_IJCNN.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02387419, version 2

Citation

Mathieu Seurin, Philippe Preux, Olivier Pietquin. "I'm sorry Dave, I'm afraid I can't do that" Deep Q-Learning From Forbidden Actions. Internationnal Joint Conference on Neural Networks, Jul 2020, Glasgow, United Kingdom. ⟨hal-02387419v2⟩

Share

Metrics

Record views

138

Files downloads

371