POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learning.
Shalini JainYashas AndaluriS. VenkataKeerthyRamakrishna UpadrastaPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- partial order
- function approximation
- markov decision processes
- exploration exploitation tradeoff
- state space
- model free
- reinforcement learning algorithms
- optimal policy
- learning algorithm
- temporal difference
- machine learning
- multi agent
- policy search
- control problems
- autonomous learning
- continuous state
- learning agents
- learning classifier systems
- partially observable domains
- stable marriage
- actor critic
- markov decision process
- complex domains
- partially ordered
- action selection
- action space
- multi agent reinforcement learning
- state and action spaces
- optimal control
- partially ordered sets
- transfer learning