Llara: Supercharging robot learning data for vision-language policy
LLMs with visual inputs, ie, Vision Language Models (VLMs), have the capacity to process
state information as visual-textual prompts and respond with policy decisions in text. We …
state information as visual-textual prompts and respond with policy decisions in text. We …
Crossway diffusion: Improving diffusion-based visuomotor policy via self-supervised learning
Diffusion models have been adopted for behavioral cloning in a sequence modeling
fashion, benefiting from their exceptional capabilities in modeling complex data distributions …
fashion, benefiting from their exceptional capabilities in modeling complex data distributions …
Learning viewpoint-agnostic visual representations by recovering tokens in 3d space
Humans are remarkably flexible in understanding viewpoint changes due to visual cortex
supporting the perception of 3D structure. In contrast, most of the computer vision models …
supporting the perception of 3D structure. In contrast, most of the computer vision models …
Enhancing parcel singulation efficiency through transformer-based position attention and state space augmentation
Parcel singulation has emerged as a critical bottleneck in the swiftly advancing logistics
processes. In the pursuit of a balance between cost-effectiveness and singulation efficiency …
processes. In the pursuit of a balance between cost-effectiveness and singulation efficiency …
Weighting online decision transformer with episodic memory for offline-to-online reinforcement learning
Offline reinforcement learning (RL) has been shown to be successfully modeled as a
sequence modeling problem, drawing inspiration from the success of Transformers. Offline …
sequence modeling problem, drawing inspiration from the success of Transformers. Offline …
Prescribed safety performance imitation learning from a single expert dataset
Existing safe imitation learning (safe IL) methods mainly focus on learning safe policies that
are similar to expert ones, but may fail in applications requiring different safety constraints. In …
are similar to expert ones, but may fail in applications requiring different safety constraints. In …
Active vision reinforcement learning under limited visual observability
In this work, we investigate Active Vision Reinforcement Learning (ActiveVision-RL), where
an embodied agent simultaneously learns action policy for the task while also controlling its …
an embodied agent simultaneously learns action policy for the task while also controlling its …
In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
Offline preference-based reinforcement learning (PbRL) typically operates in two phases:
first, use human preferences to learn a reward model and annotate rewards for a reward …
first, use human preferences to learn a reward model and annotate rewards for a reward …
[PDF][PDF] Pre-controller for Safe Reinforcement Learning using Transformer with State-Action-Reward Representations
Z Shen - 2024 - waseda.repo.nii.ac.jp
Reinforcement Learning (RL) is a dynamic and influential field within artificial intelligence
that focuses on how agents should take actions in an environment to maximize a cumulative …
that focuses on how agents should take actions in an environment to maximize a cumulative …