Solving Partially Observable 3D-Visual Tasks with Visual Radial Basis Function Network and Proximal Policy Optimization.
Julien HautotCéline TeulièreNourddine AzzaouiPublished in: Mach. Learn. Knowl. Extr. (2023)
Keyphrases
- visual tasks
- partially observable
- markov decision problems
- radial basis function network
- active vision
- decision problems
- reinforcement learning
- state space
- partially observable environments
- dynamical systems
- markov decision processes
- infinite horizon
- reward function
- optimal policy
- belief state
- neural network
- inverse reinforcement learning
- fuzzy model
- radial basis function
- dynamic programming
- computational framework
- planning domains
- multilayer perceptron
- self organizing maps
- sufficient conditions
- utility function