180 citations · 519 across the 23 of their papers we have counts for
11 papers · 1 filter
Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?
Gunshi Gupta, Tim G. J. Rudner, Rowan Thomas McAllister +2
Causal confusion is a phenomenon where an agent learns a policy that reflects imperfect spurious correlations in the data. Such a policy may falsely appear to be optimal during tra…
RAP: Risk-Aware Prediction for Robust Planning
Haruki Nishimura, Jean Mercat, Blake Wulfe +2
Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is…
Control-Aware Prediction Objectives for Autonomous Driving
Rowan McAllister, Blake Wulfe, Jean Mercat +3
Autonomous vehicle software is typically structured as a modular pipeline of individual components (e.g., perception, prediction, and planning) to help separate concerns into inter…
Dynamics-Aware Comparison of Learned Reward Functions
Blake Wulfe, Ashwin Balakrishna, Logan Ellis +3
The ability to learn reward functions plays an important role in enabling the deployment of intelligent agents in the real world. However, comparing reward functions, for example a…
Outcome-Driven Reinforcement Learning via Variational Inference
Tim G. J. Rudner, Vitchyr H. Pong, Rowan McAllister +2
While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manu…
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Angelos Filos, Panagiotis Tigas, Rowan McAllister +3
Out-of-training-distribution (OOD) scenarios are a common challenge of learning agents at deployment, typically leading to arbitrary deductions and poorly-informed decisions. In pr…
Learning Invariant Representations for Reinforcement Learning without Reconstruction
Amy Zhang, Rowan McAllister, Roberto Calandra +2
We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstructio…
Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
Brijen Thananjeyan, Ashwin Balakrishna, Ugo Rosolia +6
Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncert…
Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty
Rowan McAllister, Gregory Kahn, Jeff Clune +1
Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to thei…
Deep Imitative Models for Flexible Inference, Planning, and Control
Nicholas Rhinehart, Rowan McAllister, Sergey Levine
Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based…
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
Kurtland Chua, Roberto Calandra, Rowan McAllister +1
Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. T…