Ajin Joseph

According to our database, Ajin Joseph authored at least 16 papers between 2015 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement.

Samuel Neumann, Sungsu Lim, Ajin George Joseph, Yangchen Pan, Adam White, Martha White

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Monotonic Model Improvement Self-Play Algorithm for Adversarial Games.

Poorna Syama Sundar, Manjunath Vasam, Ajin George Joseph

Proceedings of the 62nd IEEE Conference on Decision and Control, 2023

2019

Two-Timescale Networks for Nonlinear Value Function Approximation.

Wesley Chung, Somjit Nath, Ajin Joseph, Martha White

Proceedings of the 7th International Conference on Learning Representations, 2019

An Adaptive and Incremental Approach to Quantile Estimation.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the 58th IEEE Conference on Decision and Control, 2019

Stochastic Approximation Trackers for Model-Based Search.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the 57th Annual Allerton Conference on Communication, 2019

2018

An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method.

Ajin George Joseph, Shalabh Bhatnagar

Mach. Learn., 2018

An incremental off-policy search in a model-free Markov decision process using a single sample path.

Ajin George Joseph, Shalabh Bhatnagar

Mach. Learn., 2018

Actor-Expert: A Framework for using Action-Value Methods in Continuous Action Spaces.

Sungsu Lim, Ajin Joseph, Lei Le, Yangchen Pan, Martha White

CoRR, 2018

A Cross Entropy based Optimization Algorithm with Global Convergence Guarantees.

Ajin George Joseph, Shalabh Bhatnagar

CoRR, 2018

2017

An Incremental Fast Policy Search Using a Single Sample Path.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the Pattern Recognition and Machine Intelligence, 2017

Bounds for off-policy prediction in reinforcement learning.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the 2017 International Joint Conference on Neural Networks, 2017

A model based search method for prediction in model-free Markov decision process.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the 2017 International Joint Conference on Neural Networks, 2017

2016

A Cross Entropy based Stochastic Approximation Algorithm for Reinforcement Learning with Linear Function Approximation.

Ajin George Joseph, Shalabh Bhatnagar

CoRR, 2016

A randomized algorithm for continuous optimization.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the Winter Simulation Conference, 2016

Revisiting the Cross Entropy Method with Applications in Stochastic Global Optimization and Reinforcement Learning.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the ECAI 2016 - 22nd European Conference on Artificial Intelligence, 29 August-2 September 2016, The Hague, The Netherlands, 2016

2015

A Stochastic Approximation Algorithm for Quantile Estimation.

Ajin George Joseph, Shalabh Bhatnagar

Proceedings of the Neural Information Processing - 22nd International Conference, 2015