Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective.
Sindre Benjamin RemmanBjørn Andreas KristiansenAnastasios M. LekkasPublished in: CoRR (2024)
Keyphrases
- optimal control
- reinforcement learning
- latent space
- control problems
- dynamic programming
- latent variables
- transfer learning
- control strategy
- optimal control problems
- low dimensional
- dimensionality reduction
- gaussian process
- high dimensional
- probabilistic latent semantic analysis
- gaussian processes
- model free
- state space
- lower dimensional
- parameter space
- feature space
- learning algorithm
- distance metric
- high dimensional data
- generative model
- gaussian process latent variable models
- matrix factorization
- neural network
- distance measure