A gradient-based reinforcement learning approach to dynamic pricing in partially-observable environments.
David VengerovPublished in: Future Gener. Comput. Syst. (2008)
Keyphrases
- partially observable environments
- dynamic pricing
- reinforcement learning
- reinforcement learning algorithms
- partially observable
- inverse reinforcement learning
- model free
- supply chain management
- learning curve
- partially observable markov decision processes
- cooperative games
- function approximation
- markov decision processes
- machine learning
- online auctions
- decision problems
- supply chain
- multiagent systems
- multi agent
- state space
- lower bound