Faster Approximate Dynamic Programming by Freezing Slow States.
Yijia WangDaniel R. JiangPublished in: CoRR (2023)
Keyphrases
- approximate dynamic programming
- linear program
- stochastic dynamic programming
- reinforcement learning
- dynamic programming
- step size
- factored mdps
- control policy
- policy iteration
- average cost
- markov decision problems
- machine learning
- linear programming
- markov decision processes
- least squares
- data mining
- initial state
- state transitions
- control system