
Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning(click it !)
Accepted to: AAMAS 2022
Authors: Naman Shah, and Siddharth Srivastava
Leader: Xiaohan
Venue: Online
Date: 3:30-4:30 p.m. May. 11th, 2022
Join Meeting: https://binghamton.zoom.us/j/99121918956 (click it!)

Descriptive and Prescriptive Visual Guidance to Improve Shared Situational Awareness in Human-Robot Teaming(click it !)
Accepted to: AAMAS 2022
Authors: Aaquib Tabrez, Matthew B. Luebbers and Bradley Hayes
Leader: Kishan
Venue: Online
Date: 3:30-4:30 p.m. April. 27th, 2022
Join Meeting: https://binghamton.zoom.us/j/99121918956 (click it!)

Deep Variational Reinforcement Learning for POMDPs Accepted to: ICML 2018(click it !)
Accepted to: ICML 2018
Authors: Maximilian Igl, Luisa Zintgraf, Tuan Anh Le, Frank Wood, Shimon Whiteson
Leader: Yohei
Venue: Online
Date: 3:30-4:30 p.m. April. 20th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances(click it !)
Accepted to: ???
Authors: Michacel Ahn, Anthony Brohan, Noah Brown, et al.
Leader: Yan
Venue: Online
Date: 3:30-4:30 p.m. April. 13rd, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue(click it !)
Accepted to: ???
Authors: Maximillian Chen, Weiyan Shi, Feifan Yan, et.al
Leader: Yohei
Venue: Online
Date: 3:30-4:30 p.m. April. 6th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Learning Feasibility to Imitate Demonstrators with Different Dynamics(click it !)
Accepted to: CoRL 2021
Authors: Zhangjie Cao, Yilun Hao, Mengxi Li, Dorsa Sadigh
Leader: Dave
Venue: Online
Date: 3:30-4:30 p.m. Mar. 30th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Pre-Trained Language Models for Interactive Decision-Making(click it !)
Accepted to: ???
Authors: Shuang Li, Xavier Puig, Chris Paxton, et al.
Leader: Yan
Venue: Online
Date: 3:30-4:30 p.m. Mar. 16th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Unwinding Rotations Improves User Comfort with Immersive Telepresence Robots(click it !)
Accepted to: ???
Authors: Markku Suomalainen, Basak Sakcak, et al.
Leader: Kishan
Venue: Online
Date: 3:30-4:30 p.m. Mar. 9th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Outracing champion Gran Turismo drivers with deep reinforcement learning(click it !)
Accepted to: Nature 2022
Authors: Peter R. Wurman, Samuel Barrett, Kenta Kawamoto, et al.
Leader: Yohei
Venue: Online
Date: 3:30-4:30 p.m. Mar. 2nd, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Visual Semantic Navigation Using Scene Priors(click it !)
Accepted to: ICLR 2019
Authors: Wei Yang, Xiaolong Wang, Ali Farhadi, Abhinav Gupta, Roozbeh Mottaghi
Leader: Saeid
Venue: Online
Date: 3:30-4:30 p.m. Feb. 16th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents(click it !)
Accepted to: ?
Authors: Wenlong Huang, Pieter Abbeel, Deepak Pathak, Igor Mordatch
Leader: Yan
Venue: Online
Date: 3:30-4:30 p.m. Feb. 09th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines(click it !)
Accepted to: AAAI 2021
Authors: Murugesan K, Atzeni M, Kapanipathi P, Shukla P, Kumaravel S, Tesauro G, Talamadupula K, Sachan M, Campbell M.
Leader: Xiaohan
Venue: Online
Date: 3:30-4:30 p.m. Feb. 02th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Reward Machines for Vision-Based Robotic Manipulation(click it !)
Accepted to: ICRA 2021
Authors: Alberto Camacho and Jacob Varley and Andy Zeng and Deepali Jain and Atil Iscen and Dmitry Kalashnikov
Leader: Dave
Venue: Online
Date: 3:30-4:30 p.m. Jan 26th, 2022
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Decision Transformer: Reinforcement Learning via Sequence Modeling(click it !)
Accepted to: ?
Authors: Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch
Leader: Xiaohan
Venue: Online
Date: 1-2 p.m. Dec. 02th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models(click it !)
Accepted to: ?
Authors: Peter West, Chandra Bhagavatula, Jack Hessel, Jena D. Hwang, Liwei Jiang, Ronan Le Bras, Ximing Lu, Sean Welleck, Yejin Choi
Leader: Yan
Venue: Online
Date: 1-2 p.m. Nov. 18th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Flight, Camera, Action! Using Natural Language and Mixed Reality to Control a Drone(click it !)
Accepted to: ?
Authors: Huang B, Bayazit D, Ullman D, Gopalan N, Tellex S.
Leader: Kishan
Venue: Online
Date: 1-2 p.m. Nov. 04th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World(click it !)
Accepted to: ?
Authors: Laura Smith, J. Chase Kew, Xue Bin Peng, Sehoon Ha, Jie Tan, Sergey Levine
Leader: Dave
Venue: Online
Date: 1-2 p.m. Oct. 28th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Online Replanning in Belief Space for Partially Observable Task and Motion Problems(click it !)
Accepted to: IEEE ICRA
Authors: Caelan Reed Garrett, Chris Paxton, Tomas Lozano-Perez, Leslie Pack Kaelbling, Dieter Fox
Leader: Yan
Venue: Online
Date: 1-2 p.m. Oct. 21th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Elephants Don't Pack Groceries: Robot Task Planning for Low Entropy Belief States(click it !)
Accepted to: IEEE RAL
Authors: Alphonsus Adu-Bredu; Zhen Zeng; Neha Pusalkar; Odest Chadwicke Jenkins
Leader: Saeid
Venue: Online
Date: 1-2 p.m. Oct. 14th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Discovering Generalizable Skills via Automated Generation of Diverse Tasks(click it !)
Accepted to: RSS
Authors: Kuan Fang, Yuke Zhu, Silvio Savarese, Li Fei-Fei
Leader: Yohei
Venue: Online
Date: 1-2 p.m. Oct. 7th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations(click it !)
Accepted to: CoRL 2021
Authors: Ruohan Gao, Yen-Yu Chang, Shivani Mall, L. Fei-Fei, Jiajun Wu
Leader: Xiaohan
Venue: Online
Date: 1-2 p.m. Sep 30th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Explanation Augmented Feedback in Human-in-the-Loop Reinforcement Learning(click it !)
Accepted to: ?
Authors: Lin Guan, Mudit Verma, Sihang Guo, Ruohan Zhang, Subbarao Kambhampati
Leader: Dave
Venue: Online
Date: 1-2 p.m. Sep 23th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning(click it !)
Accepted to: NIPS 2018
Authors: Jiajun Wu, Ilker Yildirim, Joseph J. Lim, William T. Freeman, Joshua B. Tenenbaum
Leader: Yan
Venue: Online
Date: 1-2 p.m. May 25th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Advice-Guided Reinforcement Learning in a non-Markovian Environment(click it !)
Accepted to: AAAI 2011
Authors: Daniel Neider, Jean-Raphael Gaglione, Ivan Gavran, Ufuk Topcu, Bo Wu, Zhe Xu
Leader: Dave
Venue: Online
Date: 1-2 p.m. May 18th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning(click it !)
Accepted to: AISTATS 2011
Authors: Stéphane Ross, Geoffrey J. Gordon, J. Andrew Bagnell
Leader: Dave
Venue: Online
Date: 1-2 p.m. May 11th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Spatial Intention Maps for Multi-Agent Mobile Manipulation(click it !)
Accepted to: ICRA 2021
Authors: Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Szymon Rusinkiewicz, Thomas Funkhouser
Leader: Xiaohan
Venue: Online
Date: 1-2 p.m. May 4th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Continual Learning of Knowledge Graph Embeddings(click it !)
Accepted to: Ra-L 2021
Authors: Angel Daruna, Mehul Gupta, Mohan Sridharan, and Sonia Chernova
Leader: Saeid
Venue: Online
Date: 1-2 p.m. April 20th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

What Does BERT with Vision Look At?(click it !)
Accepted to: ACL 2020
Authors: Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh and Kai-Wei Chang
Leader: Xiaohan
Venue: Online
Date: 1-2 p.m. April 13th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Planning with Learned Object Importance in Large Problem Instancesusing Graph Neural Networks(click it !)
Accepted to: AAAI 2021
Authors: Tom Silver, Rohan Chitnis, Aidan Curtis, Joshua Tenenbaum, Tomas Lozano-Perez, Leslie Pack Kaelbling
Leader: Yan
Venue: Online
Date: 1-2 p.m. April 6th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

A formal methods approach to interpretable reinforcement learning for robotic planning(click it !)
Accepted to: Science Robotics
Authors: Xiao Li, Zachary Serlin, Guang Yang and Calin Belta
Leader: David
Venue: Online
Date: 1-2 p.m. March 30th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Learning When to Quit: Meta-Reasoning for Motion Planning (click it !)
Accepted to:
Authors: Yoonchang Sung, Leslie Pack Kaelbling, and Tomas Lozano-P'erez
Leader: Yan Ding
Venue: Online
Date: 1-2 p.m. March 23th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Ethically Compliant Sequential Decision Making (click it !)
Accepted to: AAAI 2021
Authors: Justin Svegliato, Samer B. Nashed, Shlomo Zilberstein
Leader: Saeid
Venue: Online
Date: 1-2 p.m. March 16th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs (click it !)
Accepted to: ICRA 2021
Authors: Yifeng Zhu, Jonathan Tremblay, Stan Birchfield, Yuke Zhu
Leader: Yan Ding
Venue: Online
Date: 1-2 p.m. March 9th, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Virtual Reality for Robots (click it !)
Accepted to:
Authors: Markku Suomalainen, Alexandra Q. Nilles, and Steven M. LaValle
Leader: Kishan
Venue: Online
Date: 1-2 p.m. March 2nd, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks (click it !)
Accepted to: AAAI 2021
Authors: Yuqian Jiang, Suda Bharadwaj, Bo Wu, Rishi Shah, Ufuk Topcu, and Peter Stone
Leader: David
Venue: Online
Date: 1-2 p.m. Feb 23rd, 2021
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Joint Inference of Reward Machines and Policies for Reinforcement Learning (click it !)
Accepted to: ICAPS 2020
Authors: Zhe Xu, Ivan Gavran, Yousef Ahmad, Rupak Majumdar, Daniel Neider, Ufuk Topcu, Bo Wu
Leader: David
Venue: Online
Date: 2-3 p.m. Dec 1st, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

RMM: A Recursive Mental Model for Dialogue Navigation (click it !)
Accepted to: EMNLP(2020)
Authors: Homero Roman Roman, Yonatan Bisk, Jesse Thomason, Asli Celikyilmaz, Jianfeng Gao
Leader: Saeid
Venue: Online
Date: 2-3 p.m. Oct 20th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Human-like Planning for Reaching in Cluttered Environments (click it !)
Accepted to: ICRA 2020
Authors: Mohamed Hasan, Matthew Warburton, Wisdom C. Agboh, Mehmet R. Dogar, Matteo Leonetti, He Wang, Faisal Mushtaq, Mark Mon-Williams, Anthony G. Cohn
Leader: Xiaohan Zhang
Venue: Online
Date: 2-3 p.m. Oct 13th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Making Sense of Vision and Touch: Self-Supervised Learning of multimodal Representations for Contact-Rich Tasks (click it !)
Accepted to: ICRA 2019
Authors: Michelle A. Lee∗, Yuke Zhu∗, Krishnan Srinivasan, Parth Shah, Silvio Savarese, Li Fei-Fei, Animesh Garg, Jeannette Bohg
Leader: Xiaohan Zhang
Venue: Online
Date: 2-3 p.m. Oct 6th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning (click it !)
Accepted to: ICLR 2019
Authors: Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu
Leader: Shiqi Zhang
Venue: Online
Date: 2-3 p.m. Sep 29th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

How to Build User Simulators to Train RL-based Dialog Systems (click it !)
Accepted to: EMNLP 2019
Authors: Weiyan Shi, Kun Qian, Xuewei Wang, and Zhou Yu
Leader: Xiaohan Zhang
Venue: Online
Date: 2-3 p.m. Sep 22nd, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Semantic Linking Maps for Active Visual Object Search (click it !)
Accepted to: 2020 IEEE International Conference on Robotics and Automation (ICRA)
Authors: Zhen Zeng, Adrian Röfer and Odest Chadwicke Jenkins
Leader: Saeid
Venue: Online
Date: 12-1 p.m. July 9nd, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Simultaneously Learning Transferable Symbols and Language Groundings from Perceptual Data for Instruction Following (click it !)
Accepted to: Robotics: Science and Systems (RSS, 2020)
Authors: Nakul Gopalan, Eric Rosen, George Konidaris, Stefanie Tellex
Leader: Shiqi Zhang
Venue: Online
Date: 12-1 p.m. July 2nd, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

SAIL: Simulation-Informed Active In-the-Wild Learning (click it !)
Accepted to: 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 2019
Authors: Elaine Schaertl Short; Adam Allevato; Andrea L. Thomaz
Leader: Yan Ding
Venue: Online
Date: 12-1 p.m. June 18th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Improving Grounded Natural Language Understanding through Human-Robot Dialog (click it !)
Authors: Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Nick Walker, Yuqian Jiang, Harel Yedidsion, Justin Hart, Peter Stone, and Raymond J. Mooney
Leader: Xiaohan Zhang
Venue: Online
Date: 12-1 p.m. June 11th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Proximal Policy Optimization Algorithms (click it !)
Authors: John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov
Leader: Nicholas A Abate
Venue: Online
Date: 12-1 p.m. June 4th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning on Robots (click it !)
Authors: Tiago Mota and Mohan Sridharan
Leader: Saeid Amiri
Venue: Online
Date: 12-1 p.m. May 28th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

RoomShift: Room-scale Dynamic Haptics for VR with Furniture-moving Swarm Robots (click it !)
Authors: Ryo Suzuki, Hooman Hedayati, Clement Zheng, James Bohn, Daniel Szafir, Ellen Yi-Luen Do, Mark D. Gross, Daniel Leithinger
Leader: Kishan D Chandan
Venue: Online
Date: 12-1 p.m. May 21st, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Imagination-Augmented Agents for Deep Reinforcement Learning (click it !)
Authors: Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, Demis Hassabis, David Silver, Daan Wierstra
Leader: Yan Ding
Venue: Online
Date: 12-1 p.m. May 7th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

That and There: Judging the Intent of Pointing Actions with Robotic Arms (click it !)
Authors: Malihe Alikhani, Baber Khalid, Rahul Shome, Chaitanya MitashKostas Bekris, Matthew Stone
Leader: Yan Ding
Venue: Online
Date: 12-1 p.m. Apr. 23th, 2020
Join Meeting: https://binghamton.zoom.us/j/3929288199 (click it!)

Learning from Interventions using Hierarchical Policies for Safety Learning (click it !)
Presenter:Yan Ding Venue:N09 Date:12-1 p.m. Feb. 20th, 2020
Abstract: Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert's reaction time and only learns short-term behavior. We address these limitations by 1) interpolating the expert's interventions back in time, and 2) by splitting the policy into two hierarchical levels, one that generates sub-goals for the future and another that generates actions to reach those desired sub-goals. This sub-goal prediction forces the algorithm to learn long-term behavior while also being robust to the expert's reaction time. Our experiments show that LfI using sub-goals in a hierarchical policy framework trains faster and achieves better asymptotic performance than typical LfD.

Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety (click it !)
Presenter:Yan Ding, Venue:P03, Date:12-1 p.m. Oct. 23th, 2019
Abstract: The decision and planning system for autonomousdriving in urban environments is hard to design. Most currentmethods manually design the driving policy, which can be ex-pensive to develop and maintain at scale. Instead, with imitation learning we only need to collect data and the computer willlearn and improve the driving policy automatically. However, existing imitation learning methods for autonomous driving arehardly performing well for complex urban scenarios. Moreover,the safety is not guaranteed when we use a deep neural network policy. In this paper, we proposed a framework to learnthe driving policy in urban scenarios efficiently given offline connected driving data, with a safety controller incorporatedto guarantee safety at test time. The experiments show that ourmethod can achieve high performance in realistic simulationsof urban driving scenarios.

Robot Programming Through Augmented Trajectories (IROS, 2019) (click it !)
Presenter:Kishan Chandan, Venue:P03 Date:12-1 p.m., Oct. 16th, 2019
Abstract: This paper presents a future-focused approach for robot programming based on augmented trajectories. Using a mixed reality head-mounted display (Microsoft Hololens) and a 7-DOF robot arm, we designed an augmented reality (AR) robotic interface with four interactive functions to ease the robot programming task: 1) Trajectory specification. 2) Virtual previews of robot motion. 3) Visualization of robot parameters. 4) Online reprogramming during simulation and execution. We validate our AR-robot teaching interface by comparing it with a kinesthetic teaching interface in two different scenarios as part of a pilot study: creation of contact surface path and free space path. Furthermore, we present an industrial case study that illustrates our AR manufacturing paradigm by interacting with a 7-DOF robot arm to reduce wrinkles during the pleating step of the carbon-fiber-reinforcement-polymer vacuum bagging process in a simulated scenario.

Learning to Teach in Cooperative Multiagent Reinforcement Learning (AAAI, 2019) (click it !)
Presenters:Shiqi Zhang and Saeid Amiri, Venue:G11 Date:12-1 p.m., Apr. 22th, 2019
Abstract: Collective human knowledge has clearly benefited from thefact that innovations by individuals are taught to others throughcommunication. Similar to human social groups, agents indistributed learning systems would likely benefit from com-munication to share knowledge and teach skills. The problemof teaching to improve agent learning has been investigatedby prior works, but these approaches make assumptions thatprevent application of teaching to general multiagent prob-lems, or require domain expertise for problems they can applyto. This learning to teach problem has inherent complexitiesrelated to measuring long-term impacts of teaching that com-pound the standard multiagent coordination challenges. Incontrast to existing works, this paper presents the first gen-eral framework and algorithm for intelligent agents to learn toteach in a multiagent environment. Our algorithm, Learningto Coordinate and Teach Reinforcement (LeCTR), addressespeer-to-peer teaching in cooperative multiagent reinforcementlearning. Each agent in our approach learns both when andwhat to advise, then uses the received advice to improve locallearning. Importantly, these roles are not fixed; these agentslearn to assume the role of student and/or teacher at the ap-propriate moments, requesting and providing advice in orderto improve teamwide performance and learning. Empiricalcomparisons against state-of-the-art teaching methods showthat our teaching agents not only learn significantly faster, butalso learn to coordinate in tasks where existing methods fail.

Using Natural Language for Reward Shaping in Reinforcement Learning (click it !)
Presenter:Saeid Amiri, Venue:G11 Date:12-1 p.m., Apr. 15th, 2019
Abstract: Recent reinforcement learning (RL) approacheshave shown strong performance in complex do-mains such as Atari games, but are often highlysample inefficient.A common approach to re-duce interaction time with the environment is touse reward shaping, which involves carefully de-signing reward functions that provide the agent in-termediate rewards for progress towards the goal.However, designing appropriate shaping rewards isknown to be difficult as well as time-consuming. Inthis work, we address this problem by using naturallanguage instructions to perform reward shaping.We propose the LanguagE-Action Reward Network(LEARN), a framework that maps free-form nat-ural language instructions to intermediate rewardsbased on actions taken by the agent. These inter-mediate language-based rewards can seamlessly beintegrated into any standard reinforcement learn-ing algorithm. We experiment with Montezuma’sRevenge from the Atari Learning Environment, apopular benchmark in RL. Our experiments on adiverse set of 15 tasks demonstrate that, for thesame number of interactions with the environment,language-based rewards lead to successful comple-tion of the task 60% more often on average, com-pared to learning without language.

Agile Autonomous Driving using End-to-End Deep Imitation Learning (RSS, 2018) (click it!)
Presenter:Roger Correia, Venue:P03 Date:12-1 p.m., Apr. 1st, 2019
Abstract: We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost sensors. By imitating a model predictive controller equipped with advanced sensors, we train a deep neural network control policy to map raw, high-dimensional observations to continuous steering and throttle commands. Compared with recent approaches to similar tasks, our method requires neither state estimation nor on-the-fly planning to navigate the vehicle. Our approach relies on, and experimentally validates, recent imitation learning theory. Empirically, we show that policies trained with online imitation learning overcome well-known challenges related to covariate shift and generalize better than policies trained with batch imitation learning. Built on these insights, our autonomous driving system demonstrates successful high-speed off-road driving, matching the state-of-the-art performance.

Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience (AAAI, 2019) (click it !)
Presenter:Roger Correia Venue:G11 Date:12-1 p.m. Mar. 25th, 2019
Abstract: We propose an actor-critic algorithm that uses past plan-ning experience to improve the efficiency of solving robottask-and-motion planning (TAMP) problems. TAMP plan-ners search for goal-achieving sequences of high-level op-erator instances specified by both discrete and continuousparameters. Our algorithm learns a policy for selecting thecontinuous parameters during search, using a small trainingset generated from the search trees of previously solved in-stances. We also introduce a novel fixed-length vector rep-resentation for world states with varying numbers of objectswith different shapes, based on a set of key robot configura-tions. We demonstrate experimentally that our method learnsmore efficiently from less data than standard reinforcement-learning approaches and that using a learned policy to guidea planner results in the improvement of planning efficiency.

A Network-based End-to-End Trainable Task-oriented Dialogue System (Association for Computational Linguistic, 2017) (click it !)
Presenter:Shiqi Zhang Venue:G11 Date:12-1 p.m. Mar. 11th, 2019
Abstract: Teaching machines to accomplish tasksby conversing naturally with humans ischallenging. Currently, developing task-oriented dialogue systems requires creatingmultiple components and typically this in-volves either a large amount of handcraft-ing, or acquiring costly labelled datasetsto solve a statistical learning problem foreach component. In this work we intro-duce a neural network-based text-in, text-out end-to-end trainable goal-oriented di-alogue system along with a new way ofcollecting dialogue data based on a novelpipe-lined Wizard-of-Oz framework. Thisapproach allows us to develop dialogue sys-tems easily and without making too manyassumptions about the task at hand. Theresults show that the model can conversewith human subjects naturally whilst help-ing them to accomplish tasks in a restaurantsearch domain.

Communicating Robot Motion Intent with Augmented Reality (HRI, 2018) (click it !)
Presenter:Kishan Chandan Venue:G11 Date:12-1 p.m. Mar. 4th, 2019
Abstract: Humans coordinate teamwork by conveying intent through social cues, such as gestures and gaze behaviors. However, these methods may not be possible for appearance-constrained robots that lack anthropomorphic or zoomorphic features, such as aerial robots. We explore a new design space for communicating robot motion intent by investigating how augmented reality (AR) might mediate human-robot interactions. We develop a series of explicit and implicit designs for visually signaling robot motion intent using AR, which we evaluate in a user study. We found that several of our AR designs significantly improved objective task efficiency over a baseline in which users only received physically-embodied orientation cues. In addition, our designs offer several trade-offs in terms of intent clarity and user perceptions of the robot as a teammate.

Learning Pipelines with Limited Data and Domain Knowledge (NeurIPS, 2018) (click it !)
Presenter:Saeid Amiri, Venue:G11 Date:12-1 p.m. Feb. 11st, 2019
Abstract: As machine learning becomes more widely used in practice, we need new methods to build complex intelligent systems that integrate learning with existing software,and with domain knowledge encoded as rules. As a case study, we present sucha system that learns to parse Newtonian physics problems in textbooks. This system, Nuts&Bolts, learns a pipeline process that incorporates existing code,pre-learned machine learning models, and human engineered rules. It jointly trainsthe entire pipeline to prevent propagation of errors, using a combination of labelledand unlabelled data. Our approach achieves a good performance on the parsingtask, outperforming the simple pipeline and its variants. Finally, we also show how Nuts&Boltscan be used to achieve improvements on a relation extraction taskand on the end task of answering Newtonian physics problems.

Behavioral Cloning from Observation (IJCAI, 2018) (click it !)
Presenter:Saeid Amiri, Venue:G11 Date:12-1 p.m. Feb. 11st, 2019
Abstract: Humans often learn how to perform tasks via imitation: they observe others perform a task, and then very quickly infer the appropriate actions to take based on their observations. While extending this paradigm to autonomous agents is a well-studied problem in general, there are two particular aspects that have largely been overlooked: (1) that the learning is done from observation only (i.e., without explicit action information), and (2) that the learning is typically done very quickly. In this work, we propose a two-phase, autonomous imitation learning technique called behavioral cloning from observation (BCO), that aims to provide improved performance with respect to both of these aspects. First, we allow the agent to acquire experience in a self-supervised fashion. This experience is used to develop a model which is then utilized to learn a particular task by observing an expert perform that task without the knowledge of the specific actions taken. We experimentally compare BCO to imitation learning methods, including the state-of-the-art, generative adversarial imitation learning (GAIL) technique, and we show comparable task performance in several different simulation domains while exhibiting increased learning speed after expert trajectories become available.