Time and Space: Why Imperfect Information Games are Hard

49 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Hanabi Challenge: A New Frontier for AI Research (2019, background): “s another challenging dimension of complexity for AI algorithms. As has been observed in domains like poker, imperfect information entangles how an agent should behave across multiple observed states [17, 18]. In Hanabi, we observe this when thinking of the policy as a communication protocol 7 betwe”
Rethinking Formal Models of Partially Observable Multiagent Decision Making (2019, background): “However, for the purpose of CFR-D, this type of subgame is sufficient [7].”
Deep Counterfactual Regret Minimization (2018, background): “However, most of these faster variants of CFR do not handle approximation error well (Tammelin et al., 2015; Burch, 2017; Brown & Sandholm, 2019; Schmid et al., 2019).”
Joint Policy Search for Multi-agent Collaboration with Imperfect Information (2020, background): “This decomposition issue in IG have been addressed in many previous works (e.g., CFR-D [8, 7], DeepStack [29], Reach subgame solving [4]), mainly in the context of solving subgames in a principled way in two-player zero-sum games (like Poker).”
Neural Replicator Dynamics (2019, background): “2b, in every iteration, each information-state policy over the entire game was updated for both players in an alternating fashion, i.e., the ﬁrst player’s policy was updated, then the second player’s [13, Section 4.3.6] [14].”