Trust Region Policy Optimization

By John Schulman, Sergey Levine, Pieter Abbeel, Michael I. Jordan, Philipp Moritz. International Conference on Machine Learning, 2015

8,139 citations recorded by the source corpus.

In this article, we describe a method for optimizing control policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified scheme, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO). This algorithm is effective for optimizing large nonlinear policies such as neural networks. Our experiments demonstrate its robust performance on a wide variety of tasks: learning simulated robotic swimming, hopping, and walking gaits; and playing Atari games using images of the screen as input. Despite its approximations that deviate from the theory, TRPO tends to give monotonic improvement, with little tuning of hyperparameters.

Subfields: Artificial Intelligence, Reinforcement Learning, Optimization & Training

View Paper: https://arxiv.org/abs/1502.05477

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. Pieter Abbeel
  3. Yoshua Bengio
  4. Ruslan Salakhutdinov
  5. Mohit Bansal
  6. Chelsea Finn
  7. Quoc V. Le
  8. Jianfeng Gao

In Reinforcement Learning

  1. Sergey Levine
  2. Pieter Abbeel
  3. Chelsea Finn
  4. Ofir Nachum
  5. Shimon Whiteson
  6. Shixiang Shane Gu
  7. Yuxi Li
  8. Aviral Kumar

In Optimization & Training

  1. Sergey Levine
  2. Yoshua Bengio
  3. Quoc V. Le
  4. Pieter Abbeel
  5. Michael I. Jordan
  6. Simon Lacoste-Julien
  7. Peter Richtárik
  8. Jason D. Lee

Citations in the corpus