Schedule

Schedule.

Workshop Day: January 28, 2019

Workshop Details:

Workshop Overview:

We have three sessions:
- Games & Environments (G/E)
- Autonomous Vehicles & Robotics (AV/R)
- Vision & Language (V/L)
The schedule includes 6 invited talks, 3 oral presentations and a poster session for all accepted papers.

All invited talks will be 35 minutes including questions, while oral presentations will be 15 minutes (without questions).
Abstracts for invited talks are listed following the Schedule section on this page.
The bios for all invited speakers can be found in the next page: Invited Speakers.
All papers will participate in the poster session. The list of accepted papers is at the end of this page.

The proceedings for the workshop will be published on February 1 - this page will be updated accordingly.

PDF version can be downloaded here.

Time	Session	Presenter(s)	Talk / Paper Title
9:00 - 9:25	Workshop Introduction	Marwan Mattar & Danny Lange	Welcome Message and Overview of Simulations for AI
9:25 - 10:00	Invited Talk (G/E)	Yuandong Tian	Building Scalable Framework and Environment for Reinforcement Learning
10:00 - 10:15	Paper (G/E)	Arthur Juliani	The Obstacle Tower: An AI Challenge in Vision, Control and Planning
10:15 - 10:30	Paper (G/E)	Raluca Gaina	Efficient Evolutionary Methods for Game Agent Optimisation: Model-based is Best
10:30 - 11:00	Coffee Break	-	-
11:00 - 11:35	Invited Talk (G/E)	Julian Togelius	Video Games as Environments for Learning and Planning: The Final Frontier?
11:35 - 12:10	Invited Talk (AV/R)	Shital Shah	Developing Autonomous Agents for the Open World using Simulation
12:10 - 12:25	Paper (AV/R)	Ervin Teng	Learning to Learn in Simulation
12:30 - 2:00	Break for Lunch	-	-
2:00 - 2:35	Invited Talk (AV/R)	Maciek Chociej	High-performance Rendering for Reinforcement Learning
2:35 - 3:35	Poster Session	All Authors	All Papers
3:15 - 3:45	Coffee Break	-	-
3:45 - 4:20	Invited Talk (V/L)	Manolis Savva	Towards an Embodied Simulation Platform
4:20 - 4:55	Invited Talk (V/L)	Yoav Artzi	Mapping Navigation Instructions to Continuous Control
4:55 - 5:00	Closing Remarks	Marwan Mattar	-

Yuandong Tian (Facebook AI Research)

Title: Building Scalable Framework and Environment for Reinforcement Learning
Abstract: Deep Reinforcement Learning (DRL) has made strong progress in many tasks that are traditionally considered to be difficult, such as complete information games, navigation, architecture search, etc. Although the basic principle of DRL is quite simple and straightforward, to make it work often requires substantial efforts, compared to traditional supervised training. In this talk, we introduce our recent open-sourced ELF platform: efficient, lightweight and flexible frameworks to facilitate DRL research. We show the scalability of our platforms by reproducing and open sourcing AlphaGoZero/AlphaZero framework using 2000 GPUs and 1.5 weeks, achieving super-human performance of Go AI that beats 4 top-30 professional players with 20-0. We also show usability of our platform by training agents in real-time strategy games with only a small amount of resource. The trained agent develops interesting tactics and is able to beat rule-based AIs by a large margin. On the environment side, we propose House3D that makes multi-room navigation easy with fast frame rate. With House3D, we show that model-based agent that plans ahead with uncertain information navigate in unseen environments more successfully.

Julian Togelius (New York Univ.)

Title: Video Games as Environments for Learning and Planning: The Final Frontier?

Manolis Savva (Facebook AI Research & Simon Fraser Univ.)

Yoav Artzi (Cornell Univ.)

Title: Mapping Navigation Instructions to Continuous Control
Abstract: Natural language understanding in grounded interactive scenarios is tightly coupled with the actions the system generates. The action space used determines much of the complexity of the problem and the type of reasoning required. In this talk, I will describe our approach to learning to map instructions and observations to continuous control of a realistic quadcopter drone. This scenario raises new challenging questions including how can we use demonstrations to learn to bridge the gap between the high-level concepts of language and low-level robot controls? And how do we design models that continuously observe, control, and react to a rapidly changing environment? This work uses a new publicly available evaluation benchmark and an interactive simulation environment.

Maciek Chociej (OpenAI Robotics)

Shital Shah (Microsoft Research)

Title: Developing Autonomous Agents for the Open World using Simulation
Abstract: Simulation is rapidly becoming a critical tool for the modern AI research and engineering. Ability to perform accurate simulations using physics with photorealistic rendering can help development and testing of computer vision, reinforcement learning and deep learning algorithms by making it an order of magnitude cheaper and faster. In this talk, we will explore various aspects of building such simulator through our journey developing AirSim, a physically and visually realistic simulator leveraging modern game engine platforms. We will dive into the architecture patterns as well as uncover various strengths and limitations of such approach. We will demonstrate various features of AirSim and provide quick guidance on how to get started using our open source offering. We will end our discussion with three different case studies with diverse requirements outlining our learnings in utilizing this simulation platform at Microsoft Research.

PDF links are forthcoming

The Obstacle Tower: An AI Challenge in Vision, Control and Planning
Challenges of Context and Time in Reinforcement Learning: Introducing Space Fortress as a Challenge
Situational Grounding with Multi-model Simulations
Efficient Evolutionary Methods for Game Agent Optimisation: Model-based in Best
Agents-based Adaptive Level Generation for Dynamic Difficulty Adjustment in Angry Birds
Language Grounding in Minecraft with Gated-Attention Networks
Marathon Environments: Multi-agent Continuous Control Benchmarks in a Modern Video Game Engine
Learning to Learn in Simulation
Dungeon Crawl Stone Soup as an Evaluation Domain for Artificial Intelligence