Edit Distance based RL for RNNT decoding.
Dongseong HwangChangwan RyuKhe Chai SimPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- outlier detection
- decoding algorithm
- function approximation
- distance measure
- optimal policy
- machine learning
- autonomous learning
- learning classifier systems
- state space
- genetic algorithm
- markov decision processes
- decoding process
- complex domains
- continuous domains
- partially observable domains
- image restoration
- data sets
- image transmission
- temporal difference learning
- learning agents
- markov decision process
- reinforcement learning algorithms
- action selection
- model free
- multi agent
- least squares