RL4ReAl: Reinforcement Learning for Register Allocation.
S. VenkataKeerthySiddharth JainAnilava KunduRohit AggarwalAlbert CohenRamakrishna UpadrastaPublished in: CC (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- reinforcement learning algorithms
- machine learning
- markov decision processes
- optimal policy
- temporal difference
- partially observable domains
- learning problems
- direct policy search
- dynamic programming
- rl algorithms
- temporal difference learning
- learning agents
- markov decision process
- real robot
- multi agent
- learning algorithm
- transfer learning
- partially observable
- continuous state
- function approximators
- action space
- optimal control
- policy iteration
- action selection
- allocation scheme
- autonomous learning
- approximate dynamic programming
- policy search
- reinforcement learning problems
- learning process
- real world