POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learning.
Shalini JainYashas AndaluriS. VenkataKeerthyRamakrishna UpadrastaPublished in: ISPASS (2022)
Keyphrases
- reinforcement learning
- partial order
- function approximation
- reinforcement learning algorithms
- model free
- exploration exploitation tradeoff
- temporal difference
- state space
- learning algorithm
- control problems
- markov decision processes
- approximate dynamic programming
- action space
- direct policy search
- action selection
- transfer learning
- partially ordered
- rl algorithms
- learning process
- learning problems
- machine learning
- actor critic
- reinforcement learning methods
- temporal difference learning
- learning capabilities
- optimal control
- real robot
- complex domains
- autonomous learning
- optimal policy
- stable marriage
- radial basis function