Schedule

We have accepted 52 papers. There will be 4 contributed talks.

The workshop will be hosted on the AAAI Virtual web site. There you will find a link to the Zoom meeting we will use for voice chat and presentations, and Rocket.Chat client for instant messages. The login information was sent to you from AAAI.

Poster sessions will be presented using Virtual Chair / gather.town, in Room F. You can enter at this link.. There is a map at the center bottom of the page that can guide attendees to Room F.

We're collecting feedback from the community for organizing the Hidden Information Games Competition. Please fill out this form

Start Time Type Duration Title & Speaker / Author(s)

6:00 PST
9:00 EST
15:00 CET
Intro + Mini-Tutorial 50 min Workshop overview and mini-tutorial (topics TBA).
Martin Schmid, Marc Lanctot, and Julien Pérolat.
Oral 20 min Demonstration-Efficient Inverse Reinforcement Learning in Procedurally Generated Environments.
Alessandro Sestini, Alexander Kuhnle and Andrew Bagdanov.
Invited Talk 30 min Constantinos Daskalakis

Break (20 min)

8:00 PST
11:00 EST
17:00 CET
Invited Talk 30 min Rene Carmona
Oral 20 min Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games.
Brian Zhang and Tuomas Sandholm.
Poster 30+ min Poster Session #1

Break (40 min)

10:00 PST
13:00 EST
19:00 CET
Invited Talk 30 min Lillian Ratliff
Oral 20 min How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds.
Prithviraj Ammanabrolu, Jack Urbanek, Margaret Li, Arthur Szlam, Tim Rocktaschel and Jason Weston.
Poster 30+ min Poster Session #2

Break (20 min)

11:40 PST
14:40 EST
20:40 CET
Invited Talk 30 min Rich Sutton
Oral 20 min Counterfactual Multiagent Policy Gradients and Regret Minimization in Cooperative Settings.
Chirag Chhablani and Ian Kash.
Poster 30+ min Poster Session #3





Poster Session #1



Demonstration-Efficient Inverse Reinforcement Learning in Procedurally Generated Environments.
Alessandro Sestini, Alexander Kuhnle and Andrew Bagdanov.

Behaviourally Cloning River Raid Agents.
Laurens Diels and Hussain Kazmi.

Equilibrium Learning in Combinatorial Auctions: Computing Approximate Bayesian Nash Equilibria via Pseudogradient Dynamics.
Stefan Heidekrueger, Nils Kohring, Paul Sutterer and Martin Bichler.

Stochastic Shortest Path with Adversarially Changing Costs.
Aviv Rosenberg and Yishay Mansour.

Online Learning in Non-Cooperative Configurable Markov Decision Process.
Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti and Marcello Restelli.

Learning Probably Approximately Correct Maximin Strategies in Games with Infinite Strategy Spaces.
Alberto Marchesi, Francesco Trovo and Nicola Gatti.

Optimizing AlphaMu.
Tristan Cazenave, Swann Legras and Veronique Ventos.

Value Functions for Depth-Limited Solving in Imperfect-Information Games.
Vojtech Kovarik, Dominik Seitz and Viliam Lisy.

QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning.
Pascal Leroy and Matthia Sabatelli.

Griddly: A platform for AI research in games.
Chris Bamford, Shengyi Huang and Simon Lucas.

Generalized Reinforcement Learning for Gameplay.
Francesco V. Lorenzo, Sahar Asadi, Alice Karnsund, Tianze Wang and Amir H. Payberah.

SAI: a Sensible Artificial Intelligence that Targets High Scores in Go.
Francesco Morandin, Gianluca Amato, Marco Fantozzi, Rosa Gini, Carlo Metta and Maurizio Parton.

Robust Multi-agent Q-learning in Cooperative Games with Adversaries.
Eleni Nisioti, Daan Bloembergen and Michael Kaisers.

Sound Algorithms in Imperfect Information Games.
Michal Sustr, Martin Schmid, Matej Moravcik, Neil Burch, Marc Lanctot and Michael Bowling.

Small Nash Equilibrium Certificates in Very Large Games.
Brian Zhang and Tuomas Sandholm.

Stabilizing Transformer-Based Action Sequence Generation For Q-Learning.
Gideon Stein, Arip Asadulaev and Andrey Filchenkov.

No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium.
Andrea Celli, Alberto Marchesi, Gabriele Farina and Nicola Gatti.

Sequential Halving Using Scores.
Nicolas Fabiano and Tristan Cazenave.

Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond.
Gabriele Farina and Tuomas Sandholm.



Poster Session #2



OLIVAW: Mastering Othello with neither Humans nor a Penny.
Antonio Norelli and Alessandro Panconesi.

Minimax Strikes Back.
Quentin Cohen-Solal and Tristan Cazenave.

Deep policy networks for NPC behaviors that adapt to changing design parameters in Roguelike games.
Alessandro Sestini, Alexander Kuhnle and Andrew Bagdanov.

Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games.
Brian Zhang and Tuomas Sandholm.

How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds.
Prithviraj Ammanabrolu, Jack Urbanek, Margaret Li, Arthur Szlam, Tim Rocktaschel and Jason Weston.

Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent.
Gabriele Farina, Christian Kroer and Tuomas Sandholm.

Optimistic and Adaptive Lagrangian Hedging.
Ryan D'Orazio and Ruitong Huang.

DREAM: Deep Regret Minimization with Advantage Baselines and Model-free Learning.
Eric Steinberger, Adam Lerer and Noam Brown.

Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings.
Hengyuan Hu, Adam Lerer, Noam Brown and Jakob Foerster.

Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games.
Gabriele Farina and Tuomas Sandholm.

Detecting and Adapting to Novelty in Games.
Xiangyu Peng, Jonathan Balloch and Mark Riedl.

Specializing Inter-Agent Communication in Heterogeneous Multi-Agent Reinforcement Learning using Agent Class Information.
Douglas Meneghetti and Reinaldo Bianchi.

Measuring Generalization of Deep Reinforcement Learning with Real-time Strategy Games.
Shengyi Huang and Santiago Ontanon.

Bayesian Persuasion in Online Settings.
Matteo Castiglioni, Andrea Celli, Alberto Marchesi and Nicola Gatti.

Learning to guess opponents' information in large partially observable games.
Dominik Seitz, Nikita Milyukov and Viliam Lisy.

Combining Deep Reinforcement Learning and Search for Imperfect-Information Games.
Noam Brown, Anton Bakhtin, Adam Lerer and Qucheng Gong.

Efficient Exploration of Zero-Sum Stochastic Games.
Carlos Martin and Tuomas Sandholm.



Poster Session #3



Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games.
Tyler Malloy, Tim Klinger, Miao Liu, Matthew Riemer, Gerald Tesauro and Chris Sims.

Sparsified Linear Programming for Zero-Sum Equilibrium Finding.
Brian Zhang and Tuomas Sandholm.

Counterfactual Multiagent Policy Gradients and Regret Minimization in Cooperative Settings.
Chirag Chhablani and Ian Kash.

Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation.
Tanner Fiez and Lillian Ratliff.

Stackelberg Actor-Critic: A Game-Theoretic Perspective.
Liyuan Zheng, Tanner Fiez, Zane Alumbaugh, Benjamin Chasnov and Lillian Ratliff.

Inference-Based Deterministic Messaging For Multi-Agent Communication.
Varun Bhatt and Michael Buro.

How to play Notakto: Can reinforcement learning achieve optimal play on combinatorial games?.
Zhenhua Chen, Chuhua Wang, Saul Blanco, Parth Laturia and David Crandall.

CFR-DO: A Double Oracle Algorithm for Extensive-Form Games.
Stephen McAleer, John Lanier, Pierre Baldi and Roy Fox.

Measuring the Solution Strength of Learning Agents in Adversarial Perfect Information Games.
Zaheen Ahmad, Nathan Sturtevant and Michael Bowling.

Competitive Physical Human-Robot Game Play.
Boling Yang, Golnaz Habibi and Joshua Smith.

The Effect of Antagonistic Behavior in Reinforcement Learning.
Ted Fujimoto, Timothy Doster, Adam Attarian, Jill Brandenberger and Nathan Hodas.

Bayesian Multiagent Inverse Reinforcement Learning for Policy Recommendation.
Carlos Martin and Tuomas Sandholm.

Faster Algorithms for Optimal Ex-Ante Coordinated Collusive Strategies in Extensive-Form Zero-Sum Games.
Gabriele Farina, Andrea Celli, Nicola Gatti and Tuomas Sandholm.

M-Stage Epsilon-Greedy Exploration for Reinforcement Learning.
Rohan Rao and Karthik Narasimhan.

Investigating Policy Adaptations of Deep Q-Learning Autonomous Driving Agents with Transfer Learning.
Jonathan Xu.

Human-Level Performance in No-Press Diplomacy via Equilibrium Search.
Jonathan Gray, Adam Lerer, Anton Bakhtin and Noam Brown.