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