RLIF: Interactive Imitation Learning as Reinforcement Learning (EECS-2024-17)
Jianlan Luo, Perry Dong, Simon Zhai, Yi Ma and Sergey Levine

IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies (EECS-2023-62)
Philippe Hansen-Estruch, Ilya Kostrikov, Michael Janner, Kuba Grudzien and Sergey Levine

Learning with Humans in the Loop (EECS-2020-76)
Gokul Swamy

End-to-End Robotic Reinforcement Learning without Reward Engineering (EECS-2019-40)
Avi Singh, Larry Yang, Kristian Hartikainen, Chelsea Finn and Sergey Levine

Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation (EECS-2018-47)
Gregory Kahn, Adam Villaflor, Bosen Ding, Pieter Abbeel and Sergey Levine

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation (EECS-2018-37)
YuXuan Liu, Abhishek Gupta, Pieter Abbeel and Sergey Levine

Learning Compound Multi-Step Controllers under Unknown Dynamics (EECS-2016-41)
Weiqiao Han, Sergey Levine and Pieter Abbeel

Theoretical Investigation of a Non-planar Field Effect Transistor (M122)
S.R. Levine