( events)   Timezone: »  
Tue Dec 14 05:00 AM -- 02:20 PM (PST)
Ecological Theory of Reinforcement Learning: How Does Task Design Influence Agent Learning?
Manfred Díaz · Hiroki Furuta · Elise van der Pol · Lisa Lee · Shixiang (Shane) Gu · Pablo Samuel Castro · Simon Du · Marc Bellemare · Sergey Levine

This workshop builds connections between different areas of RL centered around the understanding of algorithms and their context. We are interested in questions such as, but not limited to: (i) How can we gauge the complexity of an RL problem?, (ii) Which classes of algorithms can tackle which classes of problems?, and (iii) How can we develop practically applicable guidelines for formulating RL tasks that are tractable to solve? We expect submissions that address these and other related questions through an ecological and data-centric view, pushing forward the limits of our comprehension of the RL problem.

Introductory Remarks (Intro)
Artificial what? (Invited Talk)
Shane Legg (Live Q&A)
What makes for an interesting RL problem? (Invited Talk)
Joelle Pineau (Live Q&A)
HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning (Oral)
Grounding an Ecological Theory of Artificial Intelligence in Human Evolution (Oral)
Virtual Coffee Break (Break)
Sculpting (human-like) AI systems by sculpting their (social) environments (Invited Talk)
Pierre-Yves Oudeyer (Live Q&A)
Towards RL applications in video games and with human users (Invited Talk)
Katja Hofmann (Live Q&A)
Habitat 2.0: Training Home Assistants to Rearrange their Habitat (Oral)
Embodied Intelligence via Learning and Evolution (Contributed Talk)
A Methodology for RL Environment Research (Invited Talk)
Daniel Tanis (Live Q&A)
Virtual Coffee Break (Break)
Virtual Poster Session (Poster Session)
Environment Capacity (Invited Talk)
Benjamin van Roy (Live Q&A)
A Universal Framework for Reinforcement Learning (Invited Talk)
Warren Powell (Live Q&A)
Representation Learning for Online and Offline RL in Low-rank MDPs (Oral)
Understanding the Effects of Dataset Composition on Offline Reinforcement Learning (Oral)
Structural Assumptions for Better Generalization in Reinforcement Learning (Invited Talk)
Amy Zhang (Live Q&A)
Virtual Coffee Break (Break)
Reinforcement learning: It's all in the mind (Invited Talk)
Tom Griffiths (Live Q&A)
Curriculum-based Learning: An Effective Approach for Acquiring Dynamic Skills (Invited Talk)
Michiel van de Panne (Live Q&A)
Live Panel Discussion (Discussion Panel)
BIG-Gym: A Crowd-Sourcing Challenge for RL Environments and Behaviors (Launch)
Closing Remarks (Remarks)