Improving Real-Time Bidding in Online Advertising Using Markov Decision Processes and Machine Learning Techniques.
Parikshit SharmaPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- online advertising
- state space
- optimal policy
- finite state
- reinforcement learning
- dynamic programming
- user behavior
- transition matrices
- decision theoretic planning
- reachability analysis
- finite horizon
- policy iteration
- planning under uncertainty
- infinite horizon
- average reward
- average cost
- factored mdps
- partially observable
- machine learning
- user experience
- reinforcement learning algorithms
- display advertising
- model based reinforcement learning
- reward function
- action sets
- semi markov decision processes
- behavioral targeting
- markov decision process
- long tail
- random walk
- sufficient conditions
- multi agent
- learning algorithm