Search Results for author:
Found 16 papers, 3 papers with code
Re-Envisioning Command and Control
Future warfare will require Command and Control (C2) decision-making to occur in more complex, fast-paced, ill-structured, and demanding conditions.
Scalable Interactive Machine Learning for Future Command and Control
Future warfare will require Command and Control (C2) personnel to make decisions at shrinking timescales in complex and potentially ill-defined situations.
Crowd-PrefRL: Preference-Based Reward Learning from Crowds
In this work, we introduce Crowd-PrefRL, a framework for performing preference-based RL leveraging feedback from crowds.
Rating-based Reinforcement Learning
This paper develops a novel rating-based reinforcement learning approach that uses human ratings to obtain human guidance in reinforcement learning.
DIP-RL: Demonstration-Inferred Preference Learning in Minecraft
In machine learning for sequential decision-making, an algorithmic agent learns to interact with an environment while receiving feedback in the form of a reward signal.
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022.
Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models
In particular, we provide evidence that a learned dynamics model offers the following benefits when performing PbRL: (1) preference elicitation and policy optimization require significantly fewer environment interactions than model-free PbRL, (2) diverse preference queries can be synthesized safely and efficiently as a byproduct of standard model-based RL, and (3) reward pre-training based on suboptimal demonstrations can be performed without any environmental interaction.
Autonomously Untangling Long Cables
Cables are ubiquitous in many settings and it is often useful to untangle them.
Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models
For applications in healthcare, physics, energy, robotics, and many other fields, designing maximally informative experiments is valuable, particularly when experiments are expensive, time-consuming, or pose safety hazards.
ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning
Effective robot learning often requires online human feedback and interventions that can cost significant human time, giving rise to the central challenge in interactive imitation learning: is it possible to control the timing and length of interventions to both facilitate learning and limit burden on the human supervisor?
Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies
We present two algorithms that enhance robust cable untangling, LOKI and SPiDERMan, which operate alongside HULK, a high-level planner from prior work.
Disentangling Dense Multi-Cable Knots
Disentangling two or more cables requires many steps to remove crossings between and within cables.
LazyDAgger: Reducing Context Switching in Interactive Imitation Learning
Corrective interventions while a robot is learning to automate a task provide an intuitive method for a human supervisor to assist the robot and convey information about desired behavior.
Imitation Learning with Human Eye Gaze via Multi-Objective Prediction
In this work, we propose Gaze Regularized Imitation Learning (GRIL), a novel context-aware, imitation learning architecture that learns concurrently from both human demonstrations and eye gaze to solve tasks where visual attention provides important context.
ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes
ROIAL learns Bayesian posteriors that predict each exoskeleton user's utility landscape across four exoskeleton gait parameters.
Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits
Optimizing lower-body exoskeleton walking gaits for user comfort requires understanding users' preferences over a high-dimensional gait parameter space.
