Ronald J. Williams

发表

Learning representations by back-propagating errors

Geoffrey E. Hinton, Ronald J. Williams, David E. Rumelhart, 1986, Nature.

Learning internal representations by error propagation

Geoffrey E. Hinton, Ronald J. Williams, David E. Rumelhart, 1986 .

A MATHEMATICAL ANALYSIS OF ACTOR-CRITIC ARCHITECTURES FOR LEARNING OPTIMAL CONTROLS THROUGH INCREMENTAL DYNAMIC PROGRAMMING (cid:3)

L. Baird, Ronald J. Williams, Iii Leemon C. Baird, 1990 .

Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions

Ronald J. Williams, Leemon C. Baird, L. Baird, 1993 .

Analysis of Some Incremental Variants of Policy Iteration: First Steps Toward Understanding Actor-Cr

Ronald J. Williams, Leemon C. Baird, L. Baird, 1993 .

Efficient Learning and Planning Within the Dyna Framework

Jing Peng, Ronald J. Williams, Ronald J. Williams, 1993, Adapt. Behav..

Reinforcement Learning is Direct Adaptive Optimal Control

Richard S. Sutton, Andrew G. Barto, Ronald J. Williams, 1992, 1991 American Control Conference.

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks

Ronald J. Williams, David Zipser, Ronald J. Williams, 1989, Neural Computation.

Incremental multi-step Q-learning

Jing Peng, Ronald J. Williams, Ronald J. Williams, 1994, Machine-mediated learning.

Experimental Analysis of the Real-time Recurrent Learning Algorithm

Ronald J. Williams, David Zipser, Ronald J. Williams, 1989 .

Incremental multi-step Q-learning

Jing Peng, Ronald J. Williams, Ronald J. Williams, 1994, Machine Learning.

Gradient-based learning algorithms for recurrent networks and their computational complexity

Ronald J. Williams, David Zipser, Ronald J. Williams, 1995 .

Gradient-Based Learning Algorithms for Recurrent Networks

Ronald J. Williams, Ronald J. Williams, 1989 .

Adaptive state representation and estimation using recurrent connectionist networks

Ronald J. Williams, Ronald J. Williams, 1990 .

Partial Order Optimum Likelihood (POOL): Maximum Likelihood Prediction of Protein Active Site Residues Using 3D Structure and Sequence Properties

Ying Wei, Ronald J. Williams, Leonel F. Murga, 2009, PLoS Comput. Biol..

Enhanced performance in prediction of protein active sites with THEMATICS and support vector machines

Ronald J. Williams, W. Tong, Ying Wei, 2008, Protein science : a publication of the Protein Society.

Statistical criteria for the identification of protein active sites using theoretical microscopic titration curves

Ronald J. Williams, L. F. Murga, M. Ondrechen, 2005, Proteins.

Robust, Efficient, Globally-Optimized Reinforcement Learning with the Parti-Game Algorithm

Ronald J. Williams, Mohammad A. Al-Ansari, Ronald J. Williams, 1998, NIPS.

Modifying the Parti-game Algorithm for Increased Robustness, Higher Eeciency and Better Policies

Ronald J. Williams, M. A. Al-Ansari, 1998 .

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories

Jing Peng, Ronald J Williams, Ronald J. Williams, 1990, Neural Computation.

Gradient-based learning algorithms for recurrent connectionist networks

Ronald J. Williams, David Zipser, Ronald J. Williams, 1990 .

Dynamic recurrent neural networks: Theory and applications

C. L. Giles, C. Lee Giles, Gary M. Kuhn, 1994, IEEE Trans. Neural Networks Learn. Syst..

Learning representations of back-propagation errors

Geoffrey E. Hinton, David E. Rumelhart, Geoffrey E. Hinton, 1986 .

Incremental Multi-Step

Ronald J. Williams, Q-LearningJING Peng, 1996 .

Efficient Learning and Planning Within the Dyna Framework

J. Peng, R.J. Williams, Ronald J. Williams, 1993, IEEE International Conference on Neural Networks.

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Ronald J. Williams, Ronald J. Williams, 2004, Machine Learning.

Some Observations on the Use of theExtended

Ronald J. Williams, 2007 .

Function Optimization using Connectionist Reinforcement Learning Algorithms

Jing Peng, Ronald J. Williams, Ronald J. Williams, 1991 .

On the use of backpropagation in associative reinforcement learning

R. J. Williams, Ronald J. Williams, R. J. Williams, 1988, IEEE 1988 International Conference on Neural Networks.

Reinforcement Learning is Direct Adaptive Optimal Control

R. Sutton, Ronald J. Williams, A. Barto, 1992, 1991 American Control Conference.

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

R. J. Williams, Ronald J. Williams, 2004, Machine Learning.

Training recurrent networks using the extended Kalman filter

Ronald J. Williams, Ronald J. Williams, R.J. Williams, 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

Reinforcement learning algorithms as function optimizers

J. Peng, R. J. Williams, Ronald J. Williams, 1989, International 1989 Joint Conference on Neural Networks.

Reinforcement learning is direct adaptive optimal control

R.J. Williams, R.S. Sutton, A.G. Barto, 1991, IEEE Control Systems.

Learning internal representations by error propagation

Geoffrey E. Hinton, D. Rumelhart, Ronald J. Williams, 1986 .

An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories

Ronald J. Williams, Jing Peng, 1990, Neural Computation.

Simple statistical gradient-following algorithms for connectionist reinforcement learning

Ronald J. Williams, 1992, Machine Learning.