539 citations · 1.5k across the 37 of their papers we have counts for
16 papers · 1 filter
TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching
Yecheng Jason Ma, Kausik Sivakumar, Jason Yan +2
Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrel…
Planning Goals for Exploration
Edward S. Hu, Richard Chang, Oleh Rybkin +1
Dropped into an unknown environment, what should an agent do to quickly learn about the environment and how to accomplish diverse tasks within it? We address this question within t…
Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning
Kun Huang, Edward S. Hu, Dinesh Jayaraman
Physical interactions can often help reveal information that is not readily apparent. For example, we may tug at a table leg to evaluate whether it is built well, or turn a water b…
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
Chuan Wen, Jianing Qian, Jierui Lin +3
Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor c…
How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via -Advantage Regression
Yecheng Jason Ma, Jason Yan, Dinesh Jayaraman +1
Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\text…
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching
Yecheng Jason Ma, Andrew Shen, Dinesh Jayaraman +1
We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-o…
Prospective Learning: Principled Extrapolation to the Future
Ashwin De Silva, Rahul Ramesh, Lyle Ungar +40
Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the…
Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning
Yecheng Jason Ma, Andrew Shen, Osbert Bastani +1
Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reduci…
Conservative Offline Distributional Reinforcement Learning
Yecheng Jason Ma, Dinesh Jayaraman, Osbert Bastani
Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requi…
Keyframe-Focused Visual Imitation Learning
Chuan Wen, Jierui Lin, Jianing Qian +2
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories,…
How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?
Jingxi Xu, Bruce Lee, Nikolai Matni +1
The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. W…
Fighting Copycat Agents in Behavioral Cloning from Observation Histories
Chuan Wen, Jierui Lin, Trevor Darrell +2
Imitation learning trains policies to map from input observations to the actions that an expert would choose. In this setting, distribution shift frequently exacerbates the effect…
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Jesse Zhang, Brian Cheung, Chelsea Finn +2
Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome t…
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Karl Pertsch, Oleh Rybkin, Frederik Ebert +3
The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devisi…
SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
Glen Berseth, Daniel Geng, Coline Devin +4
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche. We propose that such a struggle to achieve and preserve order mi…
Causal Confusion in Imitation Learning
Pim de Haan, Dinesh Jayaraman, Sergey Levine
Behavioral cloning reduces policy learning to supervised learning by training a discriminative model to predict expert actions given observations. Such discriminative models are no…