328 citations · 1.9k across the 108 of their papers we have counts for
15 papers · 1 filter
Video Prediction Models as Rewards for Reinforcement Learning
Alejandro Escontrela, Ademi Adeniji, Wilson Yan +6
Specifying reward signals that allow agents to learn complex behaviors is a long-standing challenge in reinforcement learning. A promising approach is to extract preferences for be…
Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations
Albert Wilcox, Ashwin Balakrishna, Jules Dedieu +3
Providing densely shaped reward functions for RL algorithms is often exceedingly challenging, motivating the development of RL algorithms that can learn from easier-to-specify spar…
Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models
Vincent Lim, Ellen Novoseller, Jeffrey Ichnowski +2
For applications in healthcare, physics, energy, robotics, and many other fields, designing maximally informative experiments is valuable, particularly when experiments are expensi…
Accelerating Quadratic Optimization with Reinforcement Learning
Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato +6
First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapid…
LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks
Albert Wilcox, Ashwin Balakrishna, Brijen Thananjeyan +2
Reinforcement learning (RL) has shown impressive success in exploring high-dimensional environments to learn complex tasks, but can often exhibit unsafe behaviors and require exten…
Policy Gradient Bayesian Robust Optimization for Imitation Learning
Zaynah Javed, Daniel S. Brown, Satvik Sharma +5
The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are…
PAC Best Arm Identification Under a Deadline
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica +3
We study -PAC best arm identification, where a decision-maker must identify an -optimal arm with probability at least , while minimizing the number of arm pulls (…
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica +3
We study exploration in stochastic multi-armed bandits when we have access to a divisible resource that can be allocated in varying amounts to arm pulls. We focus in particular on…
Hierarchical Variational Imitation Learning of Control Programs
Roy Fox, Richard Shin, William Paul +5
Autonomous agents can learn by imitating teacher demonstrations of the intended behavior. Hierarchical control policies are ubiquitously useful for such learning, having the potent…
Continuous Online Learning and New Insights to Online Imitation Learning
Jonathan Lee, Ching-An Cheng, Ken Goldberg +1
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in pr…
On-Policy Robot Imitation Learning from a Converging Supervisor
Ashwin Balakrishna, Brijen Thananjeyan, Jonathan Lee +4
Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during polic…
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…
Online Learning with Continuous Variations: Dynamic Regret and Reductions
Ching-An Cheng, Jonathan Lee, Ken Goldberg +1
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in pr…
DART: Noise Injection for Robust Imitation Learning
Michael Laskey, Jonathan Lee, Roy Fox +2
One approach to Imitation Learning is Behavior Cloning, in which a robot observes a supervisor and infers a control policy. A known problem with this "off-policy" approach is that…
Multi-Level Discovery of Deep Options
Roy Fox, Sanjay Krishnan, Ion Stoica +1
Augmenting an agent's control with useful higher-level behaviors called options can greatly reduce the sample complexity of reinforcement learning, but manually designing options i…