Tentative Schedule!
Breakfast 8:00 - 8:30
8:30 - 8:50
Workshop Organizers
8:50 - 9:20
UC Berkeley
9:20 - 9:50
University of Texas (Virtual)
9:50 - 11:00
In-person talks:
09:50 - 09:55: Watch and Match: Supercharging Imitation with Regularized Optimal Transport
09:55 - 10:00: Robust Manipulation with Spatial Features
10:00 - 10:05: On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
10:05 - 10:10: Assisted Teleoperation for Scalable Robot Data Collection
10:10 - 10:15: DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics
10:15 - 10:20: SPRINT: Scalable Semantic Policy Pre-training via Language Instruction Relabeling
Virtual talks:
10:20 - 10:25: Self-Supervised Pre-training of 3D Point Cloud Networks with Image Data
10:25 - 10:30: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
10:30 - 10:35: Train Offline, Test Online: A Real Robot Learning Benchmark
10:35 - 10:40: Pre-trained Image Encoder for Data-Efficient Reinforcement Learning and Sim-to-Real transfer on Robotic-Manipulation tasks
10:40 - 10:45: Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning
10:45 - 10:50: MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
10:50 - 10:55: On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
11:00 - 11:30
Fisher & Paykel Appliances Auditorium (level 1 of OGG)
11:30- 12:00
KAIST
12:00 - 12:30
Stanford
Lunch 12:30 - 13:30
CoRL Opening Session 14:00 - 14:30
14:30 - 15:00
Virtual talks:
14:30 - 14:35: ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings
14:35 - 14:40: Visual Reinforcement Learning with Self-Supervised 3D Representations
14:40 - 14:45: Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods
14:45 - 14:50: CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning
14:55 - 15:00: On the Effectiveness of Fine-tuning Versus Meta-RL for Robot Manipulation
15:00 - 15:05: Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations (Pre-recorded)
15:05 - 15:10: Transformer Adapters for Robot Learning (Pre-recorded)
Coffee / Tea 15:10 - 15:30
15:30 - 16:00
CMU
16:00 - 16:05
16:05 - 17:00
17:00 - 17:05
Welcome Reception 18:30