The process of revising (or constructing) a policy immediately prior to
...
In their seminal work, Nayyar et al. (2013) showed that imperfect inform...
No-press Diplomacy is a complex strategy game involving both cooperation...
We consider the problem of making AI agents that collaborate well with h...
Algorithms designed for single-agent reinforcement learning (RL) general...
We extend the classic regret minimization framework for approximating
eq...
We consider the task of building strong but human-like policies in
multi...
Prior AI successes in complex games have largely focused on settings wit...
Lookahead search has been a critical component of recent AI successes, s...
Search is an important tool for computing effective policies in single- ...
The standard problem setting in Dec-POMDPs is self-play, where the goal ...
Stackelberg equilibrium is a solution concept in two-player games where ...
Prior AI breakthroughs in complex games have focused on either the purel...
The combination of deep reinforcement learning and search at both traini...
Deep counterfactual value networks combined with continual resolving pro...
We introduce DREAM, a deep reinforcement learning algorithm that finds
o...
Recent superhuman results in games have largely been achieved in a varie...
The CFR framework has been a powerful tool for solving large-scale
exten...
Counterfactual Regret Minimization (CFR) is the leading algorithm for so...
Counterfactual regret minimization (CFR) is a family of iterative algori...
A fundamental challenge in imperfect-information games is that states do...
In imperfect-information games, the optimal strategy in a subgame may de...
Counterfactual Regret Minimization (CFR) is the most popular iterative
a...