Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes

By Peter Marbach, John N. Tsitsiklis. 2003

71 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Statistics and Probability, 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. R´emi Munos
2. Razvan V. Florian
3. Sergey Levine
4. Bruno Scherrer
5. Marc G. Bellemare
6. Amir-massoud Farahmand
7. Csaba Szepesvari
8. Pieter Abbeel

In Computer Networks and Communications

1. R´emi Munos
2. Razvan V. Florian
3. Csaba Szepesvari
4. Aadirupa Saha
5. Tor Lattimore

In Statistics and Probability

1. R´emi Munos
2. Razvan V. Florian
3. Nan Jiang
4. Csaba Szepesvari
5. Bruno Scherrer
6. Amir-massoud Farahmand
7. Alekh Agarwal
8. Mohammad Ghavamzadeh

In Reinforcement Learning

1. R´emi Munos
2. Razvan V. Florian
3. Sergey Levine
4. Bruno Scherrer
5. Nan Jiang
6. Marc G. Bellemare
7. Amir-massoud Farahmand
8. Csaba Szepesvari

Citations in the corpus

• Policy Gradient in Continuous Time (2006, background): “…Weiss, 1986; Glynn, 1987) or more recently in the reinforcement learning literature (Williams, 1992; Sutton et al., 2000; Baxter and Bartlett, 2001; Marbach and Tsitsiklis, 2003)) for which the policy gradient estimate is subject to variance explosion when the discretization time-step ∆ tends to 0.”
• Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity (2007, background): “…by considering an approximation to the gradient of the long-term average of the external reward received by the agent with respect to the parameters w. Results related to the convergence of OLPOMDP to local maxima have been obtained (Bartlett & Baxter, 2000a; Marbach & Tsitsiklis, 1999, 2000).”