B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis.
Zishun YuYunzhe TaoLiyu ChenTao SunHongxia YangPublished in: CoRR (2023)
Keyphrases
- program synthesis
- reinforcement learning
- function approximation
- image compression
- inductive logic programming
- learning algorithm
- subband
- state space
- compression ratio
- bitstream
- model free
- learning process
- machine learning
- recursive programs
- transfer learning
- general purpose
- databases
- markov decision processes
- coding scheme
- learning problems
- image coding
- decision trees
- knowledge base
- information retrieval