Sequential cost-sensitive decision making with reinforcement learning

By Edwin P. D. Pednault, Naoki Abe, Bianca Zadrozny. 2002

89 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Jianfeng Gao
3. Yuxi Li
4. Yoshua Bengio
5. Pieter Abbeel
6. Li Deng
7. Lihong Li
8. Mohit Bansal

In Information Systems

1. Li Deng
2. Xiaodong He
3. Jianfeng Gao
4. Qiang Yang
5. Jie Yin
6. Rong Pan
7. David Silver
8. Charles X. F. Ling

In Reinforcement Learning

1. Sergey Levine
2. Lihong Li
3. Nan Jiang
4. Shimon Whiteson
5. Pieter Abbeel
6. R´emi Munos
7. Yuxi Li
8. Ofir Nachum

Citations in the corpus

• PGQ: Combining policy gradient and Q-learning (2016, background): “, 2013; 2015), online advertising (Pednault et al., 2002), board games (Tesauro, 1995; Silver et al.”
• Recurrent Reinforcement Learning: A Hybrid Approach (2015, methodology): “A similar approach was also taken in previous work (Pednault et al., 2002).”
• Doubly Robust Off-policy Evaluation for Reinforcement Learning (2015, background): “Examples are Pednault et al. (2002) and variants that generates approximate models by artificial trajectories (Fonteneau et al., 2013).”
• Model selection in markovian processes (2013, methodology): “[15] conducted experiments showing that a dynamic policy on data from the KDD cup in 1998 [9] outperforms a myopic policy which ignores the underlying dynamics.”
• Application of reinforcement learning to the game of Othello (2008, background): “A marketing application is described in [12], where a target selection decision in direct marketing is seen as a sequential decision problem.”
• Concurrent Reinforcement Learning from Customer Interactions (2013, methodology): “Reinforcement learning has previously been applied to sequential marketing problems (Pednault et al., 2002; Abe et al., 2002), cross-channel marketing (Abe et al., 2004), and market discount selection (Gomez-Perez et al., 2008).”
• Extracting Actionable Knowledge from Decision Trees (2007, methodology): “The work of [34] that applies MDP to customer databases allows new knowledge—probabilistic plans—to be extracted from the data sets, allowing a new type of knowledge to be discovered from the data sets.”