Paper
Proximal Policy Optimization Algorithms
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The · Authors: John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov · Published 2017-07-20 · arXiv:1707.06347
- Published
- 2017-07-20
- Authors
- 5
- arXiv
- 1707.06347
- Category
- cs.LG
Abstract
arXiv:1707.06347
John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel objective function that enables multiple epochs of minibatch updates. The new methods, which we call proximal policy optimization (PPO), have some of the benefits of trust region policy optimization (TRPO), but they are much simpler to implement, more general, and have better sample complexity (empirically). Our experiments test PPO on a collection of benchmark tasks, including simulated robotic locomotion and Atari game playing, and we show that PPO outperforms other online policy gradient methods, and overall strikes a favorable balance between sample complexity, simplicity, and wall-time.
Related papers
40
-
Center for AI Safety
-
Center for AI Standards and Innovation
-
Co-affiliated with Carnegie Mellon University
-
UK Artificial Intelligence Security Institute
-
Shanghai Jiao Tong University
-
Agentrys
-
Brown University
-
California Institute of Technology
-
Carnegie Mellon University
-
Hewlett Packard Labs
-
New York University
-
Princeton University
-
Stanford University
-
University at Buffalo
-
University of California
-
University of Illinois Urbana-Champaign
-
University of Pennsylvania
-
University of Texas
-
MATS
-
New York University
-
University of Pennsylvania