Portfolio item number 1
Short description of portfolio item number 1
Read more
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2 Read more
publications
Resource Constrained Deep Reinforcement Learning ICAPS 2019
Bhatia, A., Varakantham, P., & Kumar, A. (2019). In Proceedings of the International Conference on Automated Planning and Scheduling. URL PDF
TL;DR: Deep RL to optimize constrained resource allocation at city scale. Good results on realistic datasets.
Tuning the Hyperparameters of Anytime Planning: A Deep Reinforcement Learning Approach HSDIP 2021
Bhatia, A., Svegliato, J., & Zilberstein, S. (2021). In ICAPS Workshop on Heuristics and Search for Domain-independent Planning. URL PDF
TL;DR: Deep RL to control hyperparameters of anytime algorithms at runtime to optimize quality of the final solution. Good results on Anytime A* search algorithm.
On the Benefits of Randomly Adjusting Anytime Weighted A* SoCS 2021
Bhatia, A., Svegliato, J., & Zilberstein, S. (2021). In Proceedings of the International Symposium on Combinatorial Search. URL PDF
TL;DR: Randomized Weighted A* tunes the weight in Anytime Weighted A* randomly at runtime and outperforms every static weighted baseline.
Adaptive Rollout Length for Model-Based RL Using Model-Free Deep RL ArXiv 2022
Bhatia, A., Thomas, PS., & Zilberstein, S. (2022). In arXiv preprint arXiv:2206.02380. URL PDF
TL;DR: Meta-level deep RL to adapt the rollout-length in model-based RL non-myopically based on feedback from the learning process, such as accuracy of the model, learning progress and scarcity of samples.
Tuning the Hyperparameters of Anytime Planning: A Metareasoning Approach with Deep Reinforcement Learning ICAPS 2022
Bhatia, A., Svegliato, J., Nashed, S. B., & Zilberstein, S. (2022). In Proceedings of the International Conference on Automated Planning and Scheduling. URL PDF
TL;DR: Deep RL to determine optimal stopping point and hyperparameters of anytime algorithms at runtime to optimize utility of the final solution. Good results on Anytime A* search algorithm and RRT* motion planning algorithm.
Selecting the Partial State Abstractions of MDPs: A Metareasoning Approach with Deep Reinforcement Learning IROS 2022
Nashed, S.B., Svegliato, J., Bhatia, A., Russell S., Zilberstein, S. (2022). In IEEE/RSJ International Conference on Intelligent Robots and Systems. PDF
RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$ ArXiv 2023
Bhatia, A., Nashed, SB., & Zilberstein, S. (2023). In arXiv preprint arXiv:2306.15909. URL PDF
TL;DR: Incorporating task-specific Q-value estimates as inputs to a meta-RL policy can lead to improved generalization and better performance on long horizon tasks.
talks
Talk 1 on Relevant Topic in Your Field 2012
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown! Read more
Tutorial 1 on Relevant Topic in Your Field 2013
Published:
Talk 2 on Relevant Topic in Your Field 2014
Published:
Conference Proceeding talk 3 on Relevant Topic in Your Field 2014
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field. Read more
teaching
Teaching Assistant | CS383 Artificial Intelligence Fall 2022
Undergraduate course, College of Information & Computer Sciences, University of Massachusetts Amherst