Neurosymbolic Reinforcement Learning and Planning: A Survey.
Kamal AcharyaWaleed RazaCarlos M. J. M. Dourado JúniorAlvaro VelasquezHoubing SongPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- action selection
- planning problems
- partially observable
- state space
- heuristic search
- deterministic domains
- macro actions
- machine learning
- multi agent
- plan generation
- domain independent
- function approximation
- problems in artificial intelligence
- multi agent reinforcement learning
- model free
- markov decision processes
- transfer learning
- optimal policy
- decision support
- search algorithm
- optimal control
- data sets
- temporal difference
- temporal difference learning
- partial observability
- policy search
- stochastic domains
- learning process
- neural network