作者
Pieter Abbeel
Robotics
ALP: Action-Aware Embodied Learning for Perception
Comments project website available at https://xinranliang.github.io/alp/
Video Language Planning
Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training
Comments Published at the CVPR 2023 Sight and Sound workshop
Guiding Pretraining in Reinforcement Learning with Large Language Models
Comments ICML 2023
Language-Conditioned Path Planning
Comments Conference on Robot Learning, 2023
Blockwise Parallel Transformer for Large Context Models
Language Reward Modulation for Pretraining Reinforcement Learning
Comments Code available at https://github.com/ademiadeniji/lamp
The Impact of Overall Optimization on Warehouse Automation
Comments 8 pages, 4 figures, accepted at International Conference on Intelligent Robots and Systems (IROS2023)
Convolutional Occupancy Models for Dense Packing of Complex, Novel Objects
Comments In IROS 2023. Code and dataset are available at https://sites.google.com/view/fcon-packing/
Train Offline, Test Online: A Real Robot Learning Benchmark
Comments Accepted to ICRA 2023
Improving Long-Horizon Imitation Through Instruction Prediction
Comments Published at AAAI 2023
Controllability-Aware Unsupervised Skill Discovery
Comments ICML 2023
Probabilistic Adaptation of Text-to-Video Models
Comments Project website https://video-adapter.github.io/. First two authors contributed equally
Robust and Versatile Bipedal Jumping Control through Reinforcement Learning
Comments Accepted in Robotics: Science and Systems 2023 (RSS 2023). The accompanying video is at https://youtu.be/aAPSZ2QFB-E
Temporally Consistent Transformers for Video Generation
Comments Project website: https://wilson1yan.github.io/teco
Multi-View Masked World Models for Visual Robotic Manipulation
Comments Accepted to ICML 2023. First two authors contributed equally. Project webpage: https://sites.google.com/view/mv-mwm
Video Prediction Models as Rewards for Reinforcement Learning
Comments 22 pages, 18 figures, 4 tables. under review
Masked Autoencoding for Scalable and Generalizable Decision Making
Masked World Models for Visual Control
Comments Project website: https://sites.google.com/view/mwm-rl. Accepted to CoRL 2022
Emergent Agentic Transformer from Chain of Hindsight Experience
Comments International Conference on Machine Learning (ICML) 2023
Skill-Based Reinforcement Learning with Intrinsic Reward Matching
Comments 16 pages
The False Promise of Imitating Proprietary LLMs
Self-Supervised Instance Segmentation by Grasping
Masked Trajectory Models for Prediction, Representation, and Control
Comments Accepted for publication at ICML 2023. Project webpage: https://wuphilipp.github.io/mtm/
Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
Comments In ICRA 2023. Code and dataset are available at https://segm.yuxuanliu.com/
Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments
Comments First two authors contributed equally. The final version of this paper is accepted at Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6028-6036. https://doi.org/10.1609/aaai.v36i6.20549
Instruction-Following Agents with Multimodal Transformer
Comments fixed a typo in affiliation
Foundation Models for Decision Making: Problems, Methods, and Opportunities
Preference Transformer: Modeling Human Preferences using Transformers for RL
Comments Project website: https://sites.google.com/view/preference-transformer. Accepted to ICLR 2023
