RePReL: a unified framework for integrating relational planning and reinforcement learning for effective abstraction in discrete and continuous domains.
Harsha KokelSriraam NatarajanBalaraman RavindranPrasad TadepalliPublished in: Neural Comput. Appl. (2023)
Keyphrases
- continuous domains
- reinforcement learning
- genetic algorithm
- evolutionary computation
- state space
- markov decision processes
- evolution strategy
- continuous attributes
- learning algorithm
- artificial intelligence
- image processing
- bayesian networks
- artificial neural networks
- computationally efficient
- conditional independence