Learning to Select Goals in Automated Planning with Deep-Q Learning
Núñez-Molina, Carlos, Fernández-Olivares, Juan, Pérez, Raúl
–arXiv.org Artificial Intelligence
In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions. We have trained this architecture on a video game environment used as a standard test-bed for intelligent systems applications, testing it on different levels of the same game to evaluate its generalization abilities. We have measured the performance of our approach as more training data is made available, as well as compared it with both a state-of-the-art, classical planner and the standard Deep Q-Learning algorithm. The results obtained show our model performs better than the alternative methods considered, when both plan quality (plan length) and time requirements are taken into account. On the one hand, it is more sample-efficient than standard Deep Q-Learning, and it is able to generalize better across levels. On the other hand, it reduces problem-solving time when compared with a state-of-the-art automated planner, at the expense of obtaining plans with only 9% more actions.
arXiv.org Artificial Intelligence
Jun-20-2024
- Country:
- North America
- United States
- Nevada (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- Santa Clara County > Palo Alto (0.04)
- San Diego County > San Diego (0.04)
- Los Angeles County > Pasadena (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- Puerto Rico > San Juan
- San Juan (0.04)
- United States
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Spain
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Andalusia > Granada Province
- Granada (0.04)
- Catalonia > Barcelona Province
- Netherlands > Limburg
- Maastricht (0.04)
- France > Auvergne-Rhône-Alpes
- United Kingdom > England
- North America
- Genre:
- Research Report (1.00)
- Industry:
- Leisure & Entertainment > Games > Computer Games (1.00)
- Technology: