Ajin George Joseph

20 papers A* 1A 2B 2C 1Misc 1Journal 8Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Mitigating Steady-State Bias in Off-Policy TD Learning via Distributional Correction.
Trans. Mach. Learn. Res.
Emani Naga Sai Venkata Sowmya, Amit Kesari, Ajin George Joseph
2025 A conf
Emergence of Recursive Language through Bootstrapping and Iterated Learning.
AAMAS
Vikas Kumar, Ajin George Joseph
2025 J jnl
Risk‑Seeking Reinforcement Learning via Multi‑Timescale EVaR Optimization.
Trans. Mach. Learn. Res.
Deep Kumar Ganguly, Ajin George Joseph, Sarthak Girotra, Sirish Sekhar
2024 C conf
Control of van de Vusse Reactor using Deep Reinforcement Learning.
ICARCV
Rahul Yadav Ankalugari, M. U. Abuthahir, Nabil Magbool Jan, Ajin George Joseph
2023 A* conf
Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement.
ICLR
Samuel Neumann, Sungsu Lim, Ajin George Joseph, Yangchen Pan, Adam White, Martha White
2023 — conf
Monotonic Model Improvement Self-Play Algorithm for Adversarial Games.
CDC
Poorna Syama Sundar, Manjunath Vasam, Ajin George Joseph
2019 — conf
An Adaptive and Incremental Approach to Quantile Estimation.
CDC
Ajin George Joseph, Shalabh Bhatnagar
2019 — conf
Stochastic Approximation Trackers for Model-Based Search.
Allerton
Ajin George Joseph, Shalabh Bhatnagar
2018 J jnl
A Cross Entropy based Optimization Algorithm with Global Convergence Guarantees.
CoRR
Ajin George Joseph, Shalabh Bhatnagar
2018 J jnl
An Incremental Off-policy Search in a Model-free Markov Decision Process Using a Single Sample Path.
CoRR
Ajin George Joseph, Shalabh Bhatnagar
2018 J jnl
An Online Prediction Algorithm for Reinforcement Learning with Linear Function Approximation using Cross Entropy Method.
CoRR
Ajin George Joseph, Shalabh Bhatnagar
2018 J jnl
An incremental off-policy search in a model-free Markov decision process using a single sample path.
Mach. Learn.
Ajin George Joseph, Shalabh Bhatnagar
2018 J jnl
An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method.
Mach. Learn.
Ajin George Joseph, Shalabh Bhatnagar
2017 B conf
A model based search method for prediction in model-free Markov decision process.
IJCNN
Ajin George Joseph, Shalabh Bhatnagar
2017 — conf
An Incremental Fast Policy Search Using a Single Sample Path.
PReMI
Ajin George Joseph, Shalabh Bhatnagar
2017 B conf
Bounds for off-policy prediction in reinforcement learning.
IJCNN
Ajin George Joseph, Shalabh Bhatnagar
2016 J jnl
A Cross Entropy based Stochastic Approximation Algorithm for Reinforcement Learning with Linear Function Approximation.
CoRR
Ajin George Joseph, Shalabh Bhatnagar
2016 Misc conf
A randomized algorithm for continuous optimization.
WSC
Ajin George Joseph, Shalabh Bhatnagar
2016 A conf
Revisiting the Cross Entropy Method with Applications in Stochastic Global Optimization and Reinforcement Learning.
ECAI
Ajin George Joseph, Shalabh Bhatnagar
2015 — conf
A Stochastic Approximation Algorithm for Quantile Estimation.
ICONIP (2)
Ajin George Joseph, Shalabh Bhatnagar