Search Results for author:
Found 35 papers, 17 papers with code
Active Advantage-Aligned Online Reinforcement Learning with Offline Data
Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency.
PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement
Utilizing this progress prediction as a dense reward together with an adversarial push-back, we show that PROGRESSOR enables robots to learn complex behaviors without any external supervision.
Approaching Deep Learning through the Spectral Dynamics of Weights
We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning.
Learning Actionable Counterfactual Explanations in Large State Spaces
In particular, there is a collection of actions that agents can perform that each have their own cost and each provide the agent with different sets of capabilities.
MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models
The task is question-answering: for each maze, a large language model reads the walkthrough and answers hundreds of mapping and navigation questions such as "How should you go to Attic from West of House?"
6-DoF Stability Field via Diffusion Models
A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments.
Blending Imitation and Reinforcement Learning for Robust Policy Improvement
Integral to RPI are Robust Active Policy Selection (RAPS) and Robust Policy Gradient (RPG), both of which reason over whether to perform state-wise imitation from the oracles or learn from its own value function when the learner's performance surpasses that of the oracles in a specific state.
Statler: State-Maintaining Language Models for Embodied Reasoning
In this paper, we explore a new dimension in which large language models may benefit robotics planning.
Active Policy Improvement from Multiple Black-box Oracles
We introduce MAPS and MAPS-SE, a class of policy improvement algorithms that perform imitation learning from multiple suboptimal oracles.
NeRFuser: Large-Scale Scene Representation by NeRF Fusion
A practical benefit of implicit visual representations like Neural Radiance Fields (NeRFs) is their memory efficiency: large scenes can be efficiently stored and shared as small neural nets instead of collections of images.
Invariance Through Latent Alignment
A robot's deployment environment often involves perceptual changes that differ from what it has experienced during training.
Self-Supervised Camera Self-Calibration from Video
Camera calibration is integral to robotics and computer vision algorithms that seek to infer geometric properties of the scene from visual input streams.
Language Understanding for Field and Service Robots in a Priori Unknown Environments
This progress now creates an opportunity for robots to operate not only in isolation, but also with and alongside humans in our complex environments.
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
While positive pairs can be generated reliably (e. g., as different views of the same image), it is difficult to accurately establish negative pairs, defined as samples from different images regardless of their semantic content or visual features.
Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman
In this work we perform a controlled study of human language use in a competitive team-based game, and search for useful lessons for structuring communication protocol between autonomous agents.
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
As robotics matures and increases in complexity, it is more necessary than ever that robot autonomy research be reproducible.
Concurrent Training Improves the Performance of Behavioral Cloning from Observation
In contrast, learning from observation offers a way to utilize unlabeled demonstrations (e. g., video) to perform imitation learning.
Residual Policy Learning for Shared Autonomy
Shared autonomy provides an effective framework for human-robot collaboration that takes advantage of the complementary strengths of humans and robots to achieve common goals.
Robotics
Loop Estimator for Discounted Values in Markov Reward Processes
At the working heart of policy iteration algorithms commonly used and studied in the discounted setting of reinforcement learning, the policy evaluation step estimates the value of states with samples from a Markov reward process induced by following a Markov policy in a Markov decision process.
Language-guided Semantic Mapping and Mobile Manipulation in Partially Observable Environments
Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions.
DIODE: A Dense Indoor and Outdoor DEpth Dataset
We introduce DIODE, a dataset that contains thousands of diverse high resolution color images with accurate, dense, long-range depth measurements.
Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards
We propose a new complexity measure for Markov decision processes (MDPs), the maximum expected hitting cost (MEHC).
Multigrid Neural Memory
We introduce a novel approach to endowing neural networks with emergent, long-term, large-scale memory.
Inferring Compact Representations for Efficient Natural Language Understanding of Robot Instructions
The speed and accuracy with which robots are able to interpret natural language is fundamental to realizing effective human-robot interaction.
Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning
The physical design of a robot and the policy that controls its motion are inherently coupled, and should be determined according to the task and environment.
Satellite Image-based Localization via Learned Embeddings
We propose a vision-based method that localizes a ground vehicle using publicly available satellite imagery as the only prior knowledge of the environment.
Jointly Optimizing Placement and Inference for Beacon-based Localization
The accuracy of such a beacon-based localization system depends both on how beacons are distributed in the environment, and how the robot's location is inferred based on noisy and potentially ambiguous measurements.
Coherent Dialogue with Attention-based Language Models
We model coherent conversation continuation via RNN-based dialogue models equipped with a dynamic attention mechanism.
Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation
We first decide which information to share with the user according to their preferences, using a policy trained from human demonstrations via inverse reinforcement learning.
Learning Articulated Motion Models from Visual and Lingual Signals
In this paper, we present a multimodal learning framework that incorporates both visual and lingual information to estimate the structure and parameters that define kinematic models of articulated objects.
Accurate Vision-based Vehicle Localization using Satellite Imagery
We propose a method for accurately localizing ground vehicles with the aid of satellite imagery.
On the Performance of Hierarchical Distributed Correspondence Graphs for Efficient Symbol Grounding of Robot Instructions
Natural language interfaces are powerful tools that enables humans and robots to convey information without the need for extensive training or complex graphical interfaces.
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment
We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i. e., the joint task of content selection and surface realization.
Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents.
Learning Articulated Motions From Visual Demonstration
This paper describes a method by which a robot can acquire an object model by capturing depth imagery of the object as a human moves it through its range of motion.
