Publications (15)
IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
Philippe Hansen-Estruch, Ilya Kostrikov, Michael Janner +2
Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-learning (IQL) addresses this by training a Q-function using only dataset actions thr…
Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
Katie Kang, Paula Gradu, Jason Choi +3
Learned models and policies can generalize effectively when evaluated within the distribution of the training data, but can produce unpredictable and erroneous outputs on out-of-di…
H-GAP: Humanoid Control with a Generalist Planner
Zhengyao Jiang, Yingchen Xu, Nolan Wagener +5
Humanoid control is an important research challenge offering avenues for integration into human-centric infrastructures and enabling physics-driven humanoid animations. The dauntin…
Planning with Diffusion for Flexible Behavior Synthesis
Michael Janner, Yilun Du, Joshua B. Tenenbaum +1
Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to c…
Representation Learning for Grounded Spatial Reasoning
Michael Janner, Karthik Narasimhan, Regina Barzilay
The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simu…
Entity Abstraction in Visual Model-Based Reinforcement Learning
Rishi Veerapaneni, John D. Co-Reyes, Michael Chang +5
This paper tests the hypothesis that modeling a scene in terms of entities and their local interactions, as opposed to modeling the scene globally, provides a significant benefit i…