Information-Theoretic Policy Extraction from Partial Observations.
Tom LefebvrePublished in: CoRR (2022)
Keyphrases
- information theoretic
- partial observations
- partially observable
- mutual information
- information theory
- theoretic framework
- jensen shannon divergence
- information theoretic measures
- information bottleneck
- action models
- optimal policy
- decision problems
- entropy measure
- state space
- markov decision processes
- reinforcement learning
- partially observable markov decision processes
- infinite horizon
- supervised learning
- data mining
- image sequences