Samarth Sinha

Latest

• Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
• S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics
• Uniform Priors for Data-Efficient Transfer
• DIBS: Diversity inducing Information Bottleneck in Model Ensembles
• Curriculum By Smoothing
• D2RL: Deep Dense Architectures in Reinforcement Learning