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

Mathieu Seurin 1, 2, 3 Philippe Preux 3 Olivier Pietquin 4
3 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - 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 metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/hal-02387419
Contributor : Mathieu Seurin <>
Submitted on : Friday, November 29, 2019 - 5:23:30 PM
Last modification on : Wednesday, December 4, 2019 - 1:21:35 AM

File

Sorry_Dave__I_m_afraid_I_can_t...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02387419, version 1

Collections

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. Workshop on Safety and Robustness in Decision Making (NeurIPS 2019), Dec 2019, Vancouver, Canada. ⟨hal-02387419⟩

Share

Metrics

Record views

44

Files downloads

157