Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards.
Ashwinkumar Badanidiyuru VaradarajaZhe FengTianxi LiHaifeng XuPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- markov decision processes
- model free
- machine learning
- reward shaping
- reinforcement learning algorithms
- optimal policy
- transfer learning
- optimal control
- bidding strategies
- reward function
- temporal difference
- supervised learning
- learning algorithm
- learning process
- online auctions
- neural network
- decision problems
- dynamic programming
- partially observable
- action space
- hidden state
- multi issue
- robotic control