Recent Research Topics

Reward Biased Maximum Likelihood Estimation:

The exploration-exploitation trade-off remains a challenging issue in reinforcement learning. A novel class of model-based learning algorithms, RBMLE can be applied to various learning tasks such as Markov decision processes, stochastic bandits, linear quadratic systems, and contextual bandits. Theoretical analysis shows that RBMLE has comparable regret bounds to state-of-the-art methods. Empirical results show that RBMLE outperforms existing techniques, including Upper Confidence Bound (UCB) and Thompson Sampling.

Publications:

Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems,
Akshay Mete, R. Singh & P. R. Kumar , NeurIPS 2022
Link: https://arxiv.org/abs/2201.10542

Reward Biased Maximum Likelihood Estimation ,
Akshay Mete, R. Singh & P. R. Kumar, CSS 2022 (Invited Paper)
Link: https://ieeexplore.ieee.org/abstract/document/9751189

Reward Biased Maximum Likelihood Estimation for Reinforcement Learning,
Akshay Mete, R. Singh & P. R. Kumar, L4DC 2021
Link: http://proceedings.mlr.press/v144/mete21a.html

Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits
Yu-Heng Hung, Ping-Chun Hsieh, Xi Liu, P. R. Kumar, AAAI 2021
Link:https://ojs.aaai.org/index.php/AAAI/article/view/16961/16768

Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits
Xi Liu, Ping-Chun Hsieh, Yu Heng Hung, A. Bhattacharya, P. R. Kumar, ICML 2020.
Link: https://proceedings.mlr.press/v119/liu20g.html

Safe and Multi-Objective Reinforcement Learning:

We solve an open problem in safe RL about designing algorithms to learn policies with zero or bounded constraint violation. Compared with previous OFU-based algorithms, we add different kinds of pessimism into OFU to guarantee zero or bounded violation when we have different mild assumptions. We also solve an open problem in safe RL about how to design policy gradient-based algorithms for fast global convergence. By exploiting the hidden convexity of the problem and developing an anchor-changing regularized NPG framework, we improve the convergence without further assumption. Then we extend results to more general multi-objective RL, including smooth concave scalarization and minimax scalarization.

Publications:

Learning from Few Samples: 

Motivated by the problem of learning with small sample sizes, this paper shows how to incorporate into support-vector machines (SVMs) those properties that have made convolutional neural networks (CNNs) successful. Particularly important is the ability to incorporate domain knowledge of invariances, e.g., translational invariance of images.

Publications: