Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains.
Till HofmannHector GeffnerPublished in: CoRR (2024)
Keyphrases
- fully observable
- planning problems
- planning domains
- partial observability
- partially observable
- learning algorithm
- hidden state
- markov decision problems
- decentralized control
- partially observable markov decision processes
- evolutionary algorithm
- orders of magnitude
- domain independent
- reinforcement learning
- hierarchical task networks
- learning tasks
- general purpose
- decision theoretic
- action models
- optimal control
- markov decision processes
- lower bound
- search algorithm