Policy Search through Adaptive Function Approximation for Bidding in TAC SCM.
Kyriakos C. ChatzidimitriouAndreas L. SymeonidisPericles A. MitkasPublished in: AMEC/TADA (2012)
Keyphrases
- function approximation
- policy search
- reinforcement learning
- function approximators
- reinforcement learning algorithms
- policy gradient
- radial basis function
- temporal difference
- model free
- trading agents
- learning tasks
- continuous state
- neural network
- supply chain management
- transfer learning
- markov decision processes
- online auctions
- dynamic programming
- learning algorithm
- machine learning
- partially observable markov decision processes
- action selection
- optimal policy