Reading List

• LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation
  • Date: 1-2 p.m., 09/18/2023
  • Location: N09, EB
  • Leader: Yan Ding
  • Title: LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation
  • Authors: Shuo Cheng, Danfei Xu
  • Paper Link

---

Previous Paper Reading Sessions

• 06pm Aug/28/2023 (Mon) N09, EB Leader: David Defazio Details Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism
• 04pm Apr/21/2023 (Fri) N09 & Online Leader: David Defazio Details Neural Volumetric Memory for Visual Locomotion Control
• 04pm Apr/14/2023 (Fri) N09 & Online Leader: Kishan Chandan Details Reimagining RViz: Multidimensional Augmented Reality Robot Signal Design
• 04pm Mar/31/2023 (Fri) N09 & Online Leader: Eisuke Hirota Details Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion
• 04pm Mar/24/2023 (Fri) N09 & Online Leader: Yan Ding Details Embodied Amodal Recognition: Learning to Move to Perceive Objects
• 04pm Mar/17/2023 (Fri) N09 & Online Leader: Xiaohan Zhang Details MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
• 04pm Mar/10/2023 (Fri) N09 & Online Leader: Yohei Hayamizu Details Guiding Pretraining in Reinforcement Learning with Large Language Models
• 04pm Mar/01/2023 (Wed) N09 & Online Leader: Dave DeFazio Details System Configuration and Navigation of a Guide Dog Robot: Toward Animal Guide Dog-Level Guiding Work
• 04pm Feb/10/2023 (Fri) N09 & Online Leader: Kishan Chandan Details DM2: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching
• 07pm Jan/31/2023 (Tue) N09 & Online Leader: Yan Ding Details Using Commonsense Knowledge to Answer Why-Questions
• 03pm Dec/09/2022 (Fri) Online Leader: Yohei Hayamizu Details DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following
• 03pm Dec/02/2022 (Fri) Online Leader: Yan Ding Details Learning Multi-Object Dynamics with Compositional Neural Radiance Fields
• 05pm Nov/17/2022 (Thu) N09, EB Leader: David Defazio Details Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization
• 05pm Nov/10/2022 (Thu) N09, EB Leader: Yan Ding Details Code as Policies: Language Model Programs for Embodied Control
• 05pm Nov/03/2022 (Thu) N09, EB Leader: Xiaohan Zhang Details Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion
• 05pm Oct/13/2022 (Thu) N09, EB Leader: Kishan Chandan Details Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning
• 05pm Oct/06/2022 (Thu) N09, EB Leader: David Defazio Details Robotic Guide Dog: Leading a Human with Leash-Guided Hybrid Physical Interaction
• 05pm Sep/15/2022 (Thu) N09, EB Leader: Yohei Hayamizu Details Detect, Understand, Act: A Neuro-Symbolic Hierarchical Reinforcement Learning Framework (Extended Abstract)∗
• 05pm Sep/01/2022 (Thu) N09, EB Leader: Yan Ding Details Florence: A New Foundation Model for Computer Vision
• 05pm Sep/01/2022 (Thu) N09, EB Leader: Xiaohan Zhang Details Object Goal Navigation using Goal-Oriented Semantic Exploration
• 08pm May/11/2022 (Wed) Online Leader: Xiaohan Zhang Details Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning
• 08pm Apr/27/2022 (Wed) Online Leader: Kishan Chandan Details Descriptive and Prescriptive Visual Guidance to Improve Shared Situational Awareness in Human-Robot Teaming
• 08pm Apr/20/2022 (Wed) Online Leader: Yohei Hayamizu Details Deep Variational Reinforcement Learning for POMDPs
• 08pm Apr/13/2022 (Wed) Online Leader: Yan Ding Details Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• 08pm Apr/06/2022 (Wed) Online Leader: Yohei Hayamizu Details Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue
• 08pm Mar/30/2022 (Wed) Online Leader: David Defazio Details Learning Feasibility to Imitate Demonstrators with Different Dynamics
• 08pm Mar/16/2022 (Wed) Online Leader: Yan Ding Details Pre-Trained Language Models for Interactive Decision-Making
• 08pm Mar/09/2022 (Wed) Online Leader: Kishan Chandan Details Unwinding Rotations Improves User Comfort with Immersive Telepresence Robots
• 08pm Mar/02/2022 (Wed) Online Leader: Yohei Hayamizu Details Outracing champion Gran Turismo drivers with deep reinforcement learning
• 08pm Feb/16/2022 (Wed) Online Leader: Saeid Amiri Details Visual Semantic Navigation Using Scene Priors
• 08pm Feb/09/2022 (Wed) Online Leader: Yan Ding Details Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
• 08pm Feb/02/2022 (Wed) Online Leader: Xiaohan Zhang Details Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
• 08pm Jan/26/2022 (Wed) Online Leader: David Defazio Details Reward Machines for Vision-Based Robotic Manipulation
• 06pm Dec/02/2021 (Thu) Online Leader: Xiaohan Zhang Details Decision Transformer: Reinforcement Learning via Sequence Modeling
• 06pm Nov/18/2021 (Thu) Online Leader: Yan Ding Details Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
• 06pm Nov/04/2021 (Thu) Online Leader: Kishan Chandan Details Flight, Camera, Action! Using Natural Language and Mixed Reality to Control a Drone
• 06pm Oct/28/2021 (Thu) Online Leader: David Defazio Details Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
• 06pm Oct/21/2021 (Thu) Online Leader: Yan Ding Details Online Replanning in Belief Space for Partially Observable Task and Motion Problems
• 06pm Oct/14/2021 (Thu) Online Leader: Saeid Amiri Details Elephants Don't Pack Groceries: Robot Task Planning for Low Entropy Belief States
• 06pm Oct/07/2021 (Thu) Online Leader: Yohei Hayamizu Details Discovering Generalizable Skills via Automated Generation of Diverse Tasks
• 06pm Sep/30/2021 (Thu) Online Leader: Xiaohan Zhang Details ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations
• 06pm Sep/23/2021 (Thu) Online Leader: David Defazio Details Explanation Augmented Feedback in Human-in-the-Loop Reinforcement Learning
• 06pm May/25/2021 (Tue) Online Leader: Yan Ding Details Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning
• 06pm May/18/2021 (Tue) Online Leader: David Defazio Details Advice-Guided Reinforcement Learning in a non-Markovian Environment
• 06pm May/11/2021 (Tue) Online Leader: David Defazio Details A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
• 06pm May/04/2021 (Tue) Online Leader: Xiaohan Zhang Details Spatial Intention Maps for Multi-Agent Mobile Manipulation
• 06pm Apr/20/2021 (Tue) Online Leader: Saeid Amiri Details Continual Learning of Knowledge Graph Embeddings
• 06pm Apr/13/2021 (Tue) Online Leader: Xiaohan Zhang Details What Does BERT with Vision Look At?
• 06pm Apr/06/2021 (Tue) Online Leader: Yan Ding Details Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
• 06pm Mar/30/2021 (Tue) Online Leader: David Defazio Details A formal methods approach to interpretable reinforcement learning for robotic planning
• 06pm Mar/23/2021 (Tue) Online Leader: Yan Ding Details Learning When to Quit: Meta-Reasoning for Motion Planning
• 06pm Mar/16/2021 (Tue) Online Leader: Saeid Amiri Details Ethically Compliant Sequential Decision Making
• 06pm Mar/09/2021 (Tue) Online Leader: Yan Ding Details Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs
• 06pm Mar/02/2021 (Tue) Online Leader: Kishan Chandan Details Virtual Reality for Robots
• 06pm Feb/23/2021 (Tue) Online Leader: David Defazio Details Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks
• 07pm Dec/01/2020 (Tue) Online Leader: David DeFazio Details Joint Inference of Reward Machines and Policies for Reinforcement Learning
• 07pm Oct/20/2020 (Tue) Online Leader: Saeid Amiri Details RMM: A Recursive Mental Model for Dialogue Navigation
• 07pm Oct/13/2020 (Tue) Online Leader: Xiaohan Zhang Details Human-like Planning for Reaching in Cluttered Environments
• 07pm Oct/06/2020 (Tue) Online Leader: Xiaohan Zhang Details Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
• 07pm Sep/29/2020 (Tue) Online Leader: Shiqi Zhang Details Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
• 07pm Sep/22/2020 (Tue) Online Leader: Xiaohan Zhang Details How to Build User Simulators to Train RL-based Dialog Systems
• 05pm Jul/09/2020 (Thu) Online Leader: Saeid Details Semantic Linking Maps for Active Visual Object Search
• 05pm Jul/02/2020 (Thu) Online Leader: Shiqi Zhang Details Simultaneously Learning Transferable Symbols and Language Groundings from Perceptual Data for Instruction Following
• 05pm Jun/18/2020 (Thu) Online Leader: Yan Ding Details SAIL: Simulation-Informed Active In-the-Wild Learning
• 05pm Jun/11/2020 (Thu) Online Leader: Xiaohan Zhang Details Improving Grounded Natural Language Understanding through Human-Robot Dialog
• 05pm Jun/04/2020 (Thu) Online Leader: Nicholas A Abate Details Proximal Policy Optimization Algorithms
• 05pm May/28/2020 (Thu) Online Leader: Saeid Amiri Details Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning on Robots
• 05pm May/07/2020 (Thu) Online Leader: Yan Ding Details Imagination-Augmented Agents for Deep Reinforcement Learning
• 05pm Apr/23/2020 (Thu) Online Leader: Kishan D Chandan Details RoomShift: Room-scale Dynamic Haptics for VR with Furniture-moving Swarm Robots
• 05pm Apr/23/2020 (Thu) Online Leader: Yan Ding Details That and There: Judging the Intent of Pointing Actions with Robotic Arms
• 05pm Feb/20/2020 (Thu) N09 Leader: Yan Ding Details Learning from Interventions using Hierarchical Policies for Safety Learning
• 05pm Oct/23/2019 (Wed) P03 Leader: Yan Ding Details Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety
• 05pm Oct/16/2019 (Wed) P03 Leader: Kishan Chandan Details Robot Programming Through Augmented Trajectories
• 05pm Apr/22/2019 (Mon) G11 Leader: Shiqi Zhang and Saeid Amiri Details Learning to Teach in Cooperative Multiagent Reinforcement Learning
• 05pm Apr/15/2019 (Mon) G11 Leader: Saeid Amiri Details Using Natural Language for Reward Shaping in Reinforcement Learning
• 05pm Apr/01/2019 (Mon) P03 Leader: Roger Correia Details Agile Autonomous Driving using End-to-End Deep Imitation Learning
• 05pm Mar/25/2019 (Mon) G11 Leader: Roger Correia Details Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience
• 05pm Mar/11/2019 (Mon) G11 Leader: Shiqi Zhang Details A Network-based End-to-End Trainable Task-oriented Dialogue System
• 05pm Mar/04/2019 (Mon) G11 Leader: Kishan Chandan Details Communicating Robot Motion Intent with Augmented Reality
• 05pm Feb/18/2019 (Mon) G11 Leader: Saeid Amiri Details Learning Pipelines with Limited Data and Domain Knowledge
• 05pm Feb/11/2019 (Mon) G11, EB Leader: Saied Amiri Details Behavioral Cloning from Observation