DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker

225 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.

Emergent Coordination Through Competition (2019, background): “In recent years, a number of breakthroughs in AI have been made in these domains by combining deep reinforcement learning (RL) with self-play, achieving superhuman performance at Go and Poker (Silver et al., 2016; Moravk et al., 2017).”
Solving Partially Observable Stochastic Games with Public Observations (2019, background): “For ﬁnite horizon games, the concept of public states and publicly observed actions creates separated subgames that allow designing limited-lookahead algorithms for imperfect information games (Moravcik et al. 2017; Brown, Sandholm, and Amos 2018).”
From Motor Control to Team Play in Simulated Humanoid Football (2021, background): “Pitting learning agents to play against themselves (or a pool of learning agents) has achieved superhuman performance at Go and Poker (68, 106).”
The rise and potential of large language model based agents: a survey (2025, unknown): “While agents have already excelled in pure competitive environments like chess [335], Go [50], and poker [391], LLM-based agents go further by devising uniﬁed cooperative strategies through eﬀective negotiation and collaboration in more complex scenarios [392–395].”
Deep Reinforcement Learning: An Overview (2017, methodology): “When trained with reinforcement learning, a DNC can solve a moving blocks puzzle with changing goals speciﬁed by symbol sequences.”