Bridge Bidding with Imperfect Information

DeLooze, Lori L.; Downey, James P.

doi:10.1109/cig.2007.368122

Cited by 15 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Amit et al [13] proposed a Monte Carlo sampling approach based on the human bidding system to solve the ambiguity of bidding by building a decision tree model. DeLooze and Downey [21] used a human bidding model to generate a large amount of training data and clustered the bidding process utilizing self-organizing mapping for ambiguity resolution. Nevertheless, this model can only be used to bid no trump hands effectively.…”

Section: Related Workmentioning

confidence: 99%

AI Enabled Bridge Bidding Supporting Interactive Visualization

Zhang

Liu

Lou

et al. 2022

Sensors

View full text Add to dashboard Cite

With the fast progress in perfect information game problems such as AI chess and AI Go, researchers have turned to imperfect information game problems, including Texas Hold’em and Bridge. Bridge is one of the most challenging card games that have significant research value. Bridge playing is divided into two phases: bidding and playing. This paper focuses on bridge bidding and proposes a bridge bidding service framework using deep neural networks, and supports bidding visualization for the first time. The framework consists of two parts: the bidding model (BM) with a multilayer neural network, and a visualization system. The framework predicts not only reasonable bids from the existing bidding system of humans, but also provides intuitive explanations for decisions to enable human–computer information interaction. Experimental results show that this bidding AI outperforms majority of existing systems.

show abstract

Section: Related Workmentioning

confidence: 99%

AI Enabled Bridge Bidding Supporting Interactive Visualization

Zhang

Liu

Lou

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The World Computer Bridge Championship (Wbridge5) and the silver medal winner (Synrey) adopt the Monte Carlo search method based on the human bidding system. Delooze and Downey [19] generated a large number of training data with the human bidding model, clustered the hand cards and bidding process using a self-organizing map (SOM) and learned the human bidding system using unsupervised learning. Amit and Markovitch designed a decision tree model, which uses the tree hierarchy to store the rules in the human bidding system [20].…”

Section: Related Workmentioning

confidence: 99%

The Synergy of Double Neural Networks for Bridge Bidding

Zhang

Lin

et al. 2022

Mathematics

View full text Add to dashboard Cite

Artificial intelligence (AI) has made many breakthroughs in the perfect information game. Nevertheless, Bridge, a multiplayer imperfect information game, is still quite challenging. Bridge consists of two parts: bidding and playing. Bidding accounts for about 75% of the game and playing for about 25%. Expert-level teams are generally indistinguishable at the playing level, so bidding is the more decisive factor in winning or losing. The two teams can communicate using different systems during the bidding phase. However, existing bridge bidding models focus on at most one bidding system, which does not conform to the real game rules. This paper proposes a deep reinforcement learning model that supports multiple bidding systems, which can compete with players using different bidding systems and exchange hand information normally. The model mainly comprises two deep neural networks: a bid selection network and a state evaluation network. The bid selection network can predict the probabilities of all bids, and the state evaluation network can directly evaluate the optional bids and make decisions based on the evaluation results. Experiments show that the bidding model is not limited by a single bidding system and has superior bidding performance.

show abstract

“…Imitation learning has been used in learning human bidding systems (B. Yegnanarayana et al, 1996;DeLooze & Downey, 2007). It has been shown that lookahead search can be improved by borrowing rules from human bidding systems (Gamback et al, 1993;Ginsberg, 1999).…”

Section: Computerized Bridge Programmentioning

confidence: 99%

Learning to Communicate Implicitly by Actions

Tian

Zou

Davies

et al. 2020

AAAI

View full text Add to dashboard Cite

In situations where explicit communication is limited, human collaborators act by learning to: (i) infer meaning behind their partner's actions, and (ii) convey private information about the state to their partner implicitly through actions. The first component of this learning process has been well-studied in multi-agent systems, whereas the second — which is equally crucial for successful collaboration — has not. To mimic both components mentioned above, thereby completing the learning process, we introduce a novel algorithm: Policy Belief Learning (PBL). PBL uses a belief module to model the other agent's private information and a policy module to form a distribution over actions informed by the belief module. Furthermore, to encourage communication by actions, we propose a novel auxiliary reward which incentivizes one agent to help its partner to make correct inferences about its private information. The auxiliary reward for communication is integrated into the learning of the policy module. We evaluate our approach on a set of environments including a matrix game, particle environment and the non-competitive bidding problem from contract bridge. We show empirically that this auxiliary reward is effective and easy to generalize. These results demonstrate that our PBL algorithm can produce strong pairs of agents in collaborative games where explicit communication is disabled.

show abstract

Bridge Bidding with Imperfect Information

Cited by 15 publications

References 6 publications

AI Enabled Bridge Bidding Supporting Interactive Visualization

AI Enabled Bridge Bidding Supporting Interactive Visualization

The Synergy of Double Neural Networks for Bridge Bidding

Learning to Communicate Implicitly by Actions

Contact Info

Product

Resources

About