Efficient Sample Reuse in EM-Based Policy Search

By Hirotaka Hachiya, Jan Peters, Masashi Sugiyama. 2009

19 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, 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. Anuj Mahajan
2. Tim G. J. Rudner
3. Matthew R. Fellows
4. Shimon Whiteson
5. H. Hua
6. Junwei Cao
7. Yuchao Qin
8. Chuantong Hao

In Management Science and Operations Research

1. Shimon Whiteson
2. Tim G. J. Rudner
3. Anuj Mahajan
4. Matthew R. Fellows
5. Aadirupa Saha
6. Maarten de Rijke
7. Masrour Zoghi

In Reinforcement Learning

1. Shimon Whiteson
2. Anuj Mahajan
3. Tim G. J. Rudner
4. Matthew R. Fellows
5. Chongjie Zhang
6. Tonghan Wang
7. Christian Schröder de Witt
8. Wendelin Böhmer

Citations in the corpus

• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review (2018, neutral): “…a policy parameter vector θ. Assuming r(τ) is positive and bounded and applying Jensen’s inequality results in a variety of algorithms (Peters and Schaal, 2007; Hachiya et al., 2009; Neumann, 2011; Abdolmaleki et al., 2018), including reward-weighted regression (Peters and Schaal, 2007), that…”
• Optimal energy management strategies for energy Internet via deep reinforcement learning approach (2019, methodology): “For better exploration performance, Gaussian policy [52] is used to obtain the controller at each time.”
• VIREL: A Variational Inference Framework for Reinforcement Learning (2018, methodology): “Methods that derive from the pseudo-likelihood inference framework [12, 63, 45, 25, 43, 1] and use expectationmaximisation (EM) favour risk-seeking policies [33], which can be suboptimal.”