Douzero: Mastering doudizhu with self-play deep reinforcement learning
Games are abstractions of the real world, where artificial agents learn to compete and
cooperate with other agents. While significant achievements have been made in various …
cooperate with other agents. While significant achievements have been made in various …
Perfectdou: Dominating doudizhu with perfect information distillation
As a challenging multi-player card game, DouDizhu has recently drawn much attention for
analyzing competition and collaboration in imperfect-information games. In this paper, we …
analyzing competition and collaboration in imperfect-information games. In this paper, we …
A concise review of intelligent game agent
H Li, X Pang, B Sun, K Liu - Entertainment Computing, 2024 - Elsevier
Intelligent game agents are crafted using AI technologies to mimic player behavior and
make decisions autonomously. Over the past decades, the scope of intelligent agents has …
make decisions autonomously. Over the past decades, the scope of intelligent agents has …
Douzero+: Improving doudizhu ai by opponent modeling and coach-guided learning
Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL)
in various perfect and imperfect information games. Among these games, DouDizhu, a …
in various perfect and imperfect information games. Among these games, DouDizhu, a …
Full douzero+: Improving doudizhu ai by opponent modeling, coach-guided training and bidding learning
With the development of deep reinforcement learning (DRL), much progress in various
perfect and imperfect information games has been achieved. Among these games …
perfect and imperfect information games has been achieved. Among these games …
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models
Sequential decision-making refers to algorithms that take into account the dynamics of the
environment, where early decisions affect subsequent decisions. With large language …
environment, where early decisions affect subsequent decisions. With large language …
SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast
application prospects, such as swarm control of drones, collaborative manipulation by …
application prospects, such as swarm control of drones, collaborative manipulation by …
Danzero+: Dominating the guandan game through reinforcement learning
Recent advancements have propelled artificial intelligence (AI) to showcase expertise in
intricate card games such as Mahjong, DouDizhu, and Texas Hold'em. In this work, we aim …
intricate card games such as Mahjong, DouDizhu, and Texas Hold'em. In this work, we aim …
Danzero: Mastering guandan game with reinforcement learning
The use of artificial intelligence (AI) in card games has been a widely researched topic in the
field of AI for an extended period. Recent advancements have led to AI programs exhibiting …
field of AI for an extended period. Recent advancements have led to AI programs exhibiting …
Improved learning efficiency of deep Monte-Carlo for complex imperfect-information card games
Q Luo, TP Tan - Applied Soft Computing, 2024 - Elsevier
Abstract Deep Reinforcement Learning (DRL) has achieved considerable success in games
involving perfect and imperfect information, such as Go, Texas Hold'em, Stratego, and …
involving perfect and imperfect information, such as Go, Texas Hold'em, Stratego, and …