Sotabase

Career

· Postdoctoral Researcher, University of California, Berkeley2022–

Publications (12)

Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
IEEE Transactions on Information Theory · 2021
316
cited
MADE: Exploration via Maximizing Deviation from Explored Regions
Neural Information Processing Systems · 2021
49
cited
Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian
International Conference on Learning Representations · 2022
33
cited
Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
Neural Information Processing Systems · 2023
20
cited
SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory
Neural Information Processing Systems · 2020
12
cited
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
arXiv.org · 2025
11
cited
Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
arXiv.org · 2024
8
cited
Patient-adaptable intracranial pressure morphology analysis using a probabilistic model-based approach
Physiological Measurement · 2020
5
cited
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
2026
1
cited
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
2026
1
cited
Sotabase
Paria Rashidinejad | Researcher Profile | Sotabase | Sotabase