Conference proceeding
A Closer Look at Invalid Action Masking in Policy Gradient Algorithms
The International FLAIRS Conference Proceedings, v 35
04 May 2022
Abstract
In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games. Because these games have complicated rules, an action sampled from the full discrete action distribution predicted by the learned policy is likely to be invalid according to the game rules (e.g., walking into a wall). The usual approach to deal with this problem in policy gradient algorithms is to “mask out” invalid actions and just sample from the set of valid actions. The implications of this process, however, remain under-investigated. In this paper, we 1) show theoretical justification for such a practice, 2) empirically demonstrate its importance as the space of invalid actions grows, and 3) provide further insights by evaluating different action masking regimes, such as removing masking after an agent has been trained using masking.
Metrics
60 Record Views
139 citations in Scopus
Details
- Title
- A Closer Look at Invalid Action Masking in Policy Gradient Algorithms
- Creators
- Shengyi HuangSantiago Ontañón - Drexel University
- Publication Details
- The International FLAIRS Conference Proceedings, v 35
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Scopus ID
- 2-s2.0-85131143429
- Other Identifier
- 991021869111104721