FIELD NOTES TOPIC
knowledge-guided reinforcement learning
1 note, newest first.
Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
The paper presents a new Reinforcement Learning algorithm named Neuro-Symbolic Knowledge- and Gradient-Guided Reinforcement Learning (KGRL). KGRL uses knowledge from a Datalog knowledge base to prune non-applicable…
