Error Propagation for Approximate Policy and Value Iteration.
Amir Massoud FarahmandRémi MunosCsaba SzepesváriPublished in: NIPS (2010)
Keyphrases
- error propagation
- optimal policy
- markov decision process
- error resilience
- infinite horizon
- policy iteration
- markov decision processes
- channel coding
- partially observable markov decision processes
- state space
- error resilient
- packet loss
- video quality
- compressed video
- macroblock
- reinforcement learning
- hierarchical block matching
- error concealment
- coding efficiency
- image data
- markov decision problems
- decision feedback
- multimedia