Decoding surface codes with deep reinforcement learning and probabilistic policy reuse.
Elisha Siddiqui MatekoleEsther YeRamya IyerSamuel Yen-Chi ChenPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- decoding algorithm
- policy search
- markov decision process
- reward function
- reinforcement learning algorithms
- partially observable environments
- action selection
- markov decision processes
- parity check
- state space
- reed solomon
- action space
- control policy
- probabilistic model
- error control
- error correcting
- ldpc codes
- error correction
- reinforcement learning problems
- policy iteration
- function approximators
- function approximation
- approximate dynamic programming
- actor critic
- low density parity check
- state and action spaces
- three dimensional
- bayesian networks
- model free
- dynamic programming
- uncertain data
- surface reconstruction
- d objects
- long run
- finite state
- learning objects
- policy evaluation
- optimal control
- policy gradient methods
- machine learning
- generative model
- belief networks
- markov decision problems
- infinite horizon
- temporal difference
- policy gradient
- continuous state spaces
- inverse reinforcement learning
- range data
- rl algorithms
- reinforcement learning methods
- average reward
- partially observable domains
- partially observable markov decision processes
- error detection