Learning Continuous Control Policies by Stochastic Value Gradients

We present a unified framework for learning continuous control policies using backpropagation. It supports stochastic control by treating stochasticity in the Bellman equation as a deterministic function of exogenous noise. The product is a spectrum of general policy gradient algorithms that range from model-free methods with value functions to model-based methods without value functions. We use learned models but only require observations from the environment in- stead of observations from model-predicted trajectories, minimizing the impact of compounded model errors. We apply these algorithms first to a toy stochastic control problem and then to several physics-based control problems in simulation. One of these variants, SVG(1), shows the effectiveness of learning models, value functions, and policies simultaneously in continuous domains.

[1]  David Q. Mayne,et al.  Differential dynamic programming , 1972, The Mathematical Gazette.

[2]  B. Widrow,et al.  Neural networks for self-learning control systems , 1991, IEEE Control Systems Magazine.

[3]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[4]  Michael I. Jordan,et al.  Learning Without State-Estimation in Partially Observable Markovian Decision Processes , 1994, ICML.

[5]  Richard S. Sutton,et al.  A Menu of Designs for Reinforcement Learning Over Time , 1995 .

[6]  Leemon C. Baird Residual Algorithms: Reinforcement Learning with Function Approximation , 1995, ICML.

[7]  Richard D. Braatz,et al.  On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[8]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[9]  Rémi Coulom,et al.  Reinforcement Learning Using Neural Networks, with Applications to Motor Control. (Apprentissage par renforcement utilisant des réseaux de neurones, avec des applications au contrôle moteur) , 2002 .

[10]  Ronald J. Williams Simple statistical gradient-following algorithms for connectionist reinforcement learning , 2004, Machine Learning.

[11]  Longxin Lin Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching , 2004, Machine Learning.

[12]  Martin A. Riedmiller Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method , 2005, ECML.

[13]  Richard S. Sutton,et al.  Learning to Predict by the Methods of Temporal Differences , 1988, Machine Learning.

[14]  Rémi Munos,et al.  Policy Gradient in Continuous Time , 2006, J. Mach. Learn. Res..

[15]  Pieter Abbeel,et al.  Using inaccurate models in reinforcement learning , 2006, ICML.

[16]  William D. Smart,et al.  Receding Horizon Differential Dynamic Programming , 2007, NIPS.

[17]  Pawel Wawrzynski,et al.  A Cat-Like Robot Real-Time Learning to Run , 2009, ICANNGA.

[18]  Pawel Wawrzynski,et al.  Real-time reinforcement learning by sequential Actor-Critics and experience replay , 2009, Neural Networks.

[19]  Carl E. Rasmussen,et al.  PILCO: A Model-Based and Data-Efficient Approach to Policy Search , 2011, ICML.

[20]  Michael Fairbank,et al.  Value-gradient learning , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[21]  Christopher G. Atkeson,et al.  Efficient robust policy optimization , 2012, 2012 American Control Conference (ACC).

[22]  Yuval Tassa,et al.  MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[24]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[25]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2014, ICLR.

[26]  Guy Lever,et al.  Deterministic Policy Gradient Algorithms , 2014, ICML.

[27]  Sergey Levine,et al.  Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics , 2014, NIPS.

[28]  Muhammad Ghifary,et al.  Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies , 2015, ArXiv.

[29]  I. Grondman,et al.  Online Model Learning Algorithms for Actor-Critic Control , 2015 .

[30]  Sergey Levine,et al.  Trust Region Policy Optimization , 2015, ICML.

[31]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.