Robust Policy Synthesis for Uncertain POMDPs via Convex Optimization.
Marnix SuilenNils JansenMurat CubuktepeUfuk TopcuPublished in: IJCAI (2020)
Keyphrases
- convex optimization
- norm minimization
- low rank matrix
- low rank
- interior point methods
- total variation
- optimal policy
- primal dual
- convex relaxation
- convex optimization problems
- reinforcement learning
- operator splitting
- policy gradient
- markov decision processes
- denoising
- semi definite programming
- convex formulation
- alternating direction method of multipliers
- multiresolution