Search Results for author:
Found 20 papers, 10 papers with code
The Importance of Directional Feedback for LLM-based Optimizers
We study the potential of using large language models (LLMs) as an interactive optimizer for solving maximization problems in a text space using natural language and numerical feedback.
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control
To do so, we bring a subtle but critical component of LLM training pipelines -- input tokenization via byte pair encoding (BPE) -- to the seemingly distant task of learning skills of variable time span in continuous control domains.
WindSeer: Real-time volumetric wind prediction over complex terrain aboard a small UAV
Real-time high-resolution wind predictions are beneficial for various applications including safe manned and unmanned aviation.
LLF-Bench: Benchmark for Interactive Learning from Language Feedback
We introduce a new benchmark, LLF-Bench (Learning from Language Feedback Benchmark; pronounced as "elf-bench"), to evaluate the ability of AI agents to interactively learn from natural language feedback and instructions.
Interactive Robot Learning from Verbal Correction
A key feature of OLAF is its ability to update the robot's visuomotor neural policy based on the verbal feedback to avoid repeating mistakes in the future.
Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control
Our method achieves robust performance in the real world by learning an embedding from the labeled data that aligns language not to the goal image, but rather to the desired change between the start and goal images that the instruction corresponds to.
Improving Offline RL by Blending Heuristics
We propose Heuristic Blending (HUBL), a simple performance-improving technique for a broad class of offline RL algorithms based on value bootstrapping.
PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining
A rich representation is key to general robotic manipulation, but existing approaches to representation learning require large amounts of multimodal demonstrations.
MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control
We demonstrate the utility of MoCapAct by using it to train a single hierarchical policy capable of tracking the entire MoCap dataset within dm_control and show the learned low-level component can be re-used to efficiently learn downstream high-level tasks.
The Sandbox Environment for Generalizable Agent Research (SEGAR)
A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress.
Heuristic-Guided Reinforcement Learning
On the theoretical side, we characterize properties of a good heuristic and its impact on RL acceleration.
Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL
A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks not seen during training.
Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark
We present the design of a centralized benchmark for Reinforcement Learning which can help measure Sample Efficiency and Generalization in Reinforcement Learning by doing end to end evaluation of the training and rollout phases of thousands of user submitted code bases in a scalable way.
MultiPoint: Cross-spectral registration of thermal and optical aerial imagery
This model is then deployed for fast and accurate online interest point detection.
Policy Improvement via Imitation of Multiple Oracles
In this paper, we propose the state-wise maximum of the oracle policies' values as a natural baseline to resolve conflicting advice from multiple oracles.
Safe Reinforcement Learning via Curriculum Induction
In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly.
Online Learning for Active Cache Synchronization
Existing multi-armed bandit (MAB) models make two implicit assumptions: an arm generates a payoff only when it is played, and the agent observes every payoff that is generated.
Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling
From traditional Web search engines to virtual assistants and Web accelerators, services that rely on online information need to continually keep track of remote content changes by explicitly requesting content updates from remote sources (e. g., web pages).
Autonomous Thermalling as a Partially Observable Markov Decision Process (Extended Version)
Small uninhabited aerial vehicles (sUAVs) commonly rely on active propulsion to stay airborne, which limits flight time and range.
Robotics Systems and Control
Metareasoning for Planning Under Uncertainty
Our work subsumes previously studied special cases of metareasoning and shows that in the general case, metareasoning is at most polynomially harder than solving MDPs with any given algorithm that disregards the cost of thinking.
