Emergent Discovery of Reinforced Programs using Q-Learning and Planning: A Proof of Concept.
Noah SealyMalcolm I. HeywoodPublished in: CEC (2024)
Keyphrases
- action selection
- reinforcement learning
- cooperative
- multi agent
- learning algorithm
- planning problems
- neural network
- knowledge discovery
- heuristic search
- ai planning
- state space
- function approximation
- mixed initiative
- optimal policy
- decision support
- planning process
- scientific discovery
- planning systems
- blocks world
- stochastic approximation
- planning domains
- domain independent
- monte carlo
- multi agent systems
- machine learning