A Proposal to Integrate Deep Q-Learning with Automated Planning to Improve the Performance of a Planning-Based Agent.
Carlos Núñez-MolinaIgnacio VellidoVladislav Nikolov-VasilevRaúl PérezJuan Fdez-OlivaresPublished in: CAEPIA (2021)
Keyphrases
- automated planning
- goal directed
- heuristic search
- action selection
- multi agent
- planning systems
- planning domains
- ai planning
- reinforcement learning
- single agent
- macro operators
- state space
- np hard
- interactive storytelling
- state action
- heuristic search algorithms
- classical planning
- reward function
- evaluation function
- orders of magnitude