Biography
Hi! I’m Anurag, a PostDoc at Microsoft Research. Prior to PostDoc, I finished my Ph.D. at Oregon State University under supervision of Prof. Alan Fern. My research interest broadly lies in reinforcement learning (RL) and have researched explainability in AI, model-based RL, planning, offline RL, and currently investigate abstractions and planning in RL with transformer models. If you are interested in my research or want to collaborate, please feel free to reach out.
Interests
- Artificial Intelligence
- Deep Reinforcement Learning
- Planning
- Learning Representation
Education
Ph.D. in Computer Science, 2016 - 2022
Oregon State University
Thesis: Investigating Latent State and Uncertainty Representations in Reinforcement Learning
B.E. in Computer Science, 2010 - 2014
University of Mumbai
Experience
PostDoctoral Researcher
- Research on planning and latent-state representation for reinforcement learning
Research Intern
- Research on safe reinforcement learning for systems
Research Intern
- Research on model-based reinforcement learning for control
Research Intern
- Research on multi-agent reinforcement learning
Senior Software Engineer
- Developed full-stack web-products for telecommunication space.
Software Engineer
Research Papers
Quickly discover relevant content by filtering research papers.
(2023).
PcLast: Discovering Plannable Continuous Latent States.
Arxiv.
(2022).
Offline Policy Comparison with Confidence: Benchmarks and Baselines.
DRL Workshop, ICLR.
(2020).
Dream and search to control: Latent space planning for continuous control.
DRL Workshop, ICLR.
(2019).
Explainable reinforcement learning via reward decomposition.
IJCAI.
Academic Projects
Random maze environments with different size and complexity for reinforcement learning and planning research.
Investigating real-world control data for offline reinforcement learning.
Learn a policy that outputs an action as well as the time-step for which the action should be repeated.
Investigating learning finite state representation of a world and learning optimal policy via policy iteration.
A collection of environment for multi-agent reinforcement learning research, built on top of openai-gym.
