相关论文: PerfectDou: Dominating DouDizhu with Perfect Infor…

The game of bridge consists of two stages: bidding and playing. While playing is proved to be relatively easy for computer programs, bidding is very challenging. During the bidding stage, each player knowing only his/her own cards needs to…

Policy Distillation (PD) has become an effective method to improve deep reinforcement learning tasks. The core idea of PD is to distill policy knowledge from a teacher agent to a student agent. However, the teacher-student framework…

Many real-world applications can be described as large-scale games of imperfect information. To deal with these challenging domains, prior work has focused on computing Nash equilibria in a handcrafted abstraction of the domain. In this…

We study in depth the class of games with opacity condition, which are two-player games with imperfect information in which one of the players only has imperfect information, and where the winning condition relies on the information he has…

Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner. For instance, when learning how to play a board game, usually one of the first concepts learned is how the game ends, i.e. the actions…

AI algorithms for imperfect-information games are typically compared using performance metrics on individual games, making it difficult to assess robustness across game choices. Card games are a natural domain for imperfect information due…

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve…

Sparse reward environments are known to be challenging for reinforcement learning agents. In such environments, efficient and scalable exploration is crucial. Exploration is a means by which an agent gains information about the environment.…

Knowledge Distillation (KD) methods are capable of transferring the knowledge encoded in a large and complex teacher into a smaller and faster student. Early methods were usually limited to transferring the knowledge only between the last…

A zero-sum two person Perfect Information Stochastic game (PISG) under limiting average payoff has a value and both the maximiser and the minimiser have optimal pure stationary strategies. Firstly we form the matrix of undiscounted payoffs…

Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectiveness in accelerating network training by introducing a fixed…

Traditional RLHF-based LLM alignment methods explicitly maximize the expected rewards from a separate reward model. More recent supervised alignment methods like Direct Preference Optimization (DPO) circumvent this phase to avoid problems…

Knowledge Distillation (KD), which transfers the knowledge of a well-trained large model (teacher) to a small model (student), has become an important area of research for practical deployment of recommender systems. Recently, Relaxed…

We propose InfoChess, a symmetric adversarial game that elevates competitive information acquisition to the primary objective. There is no piece capture, removing material incentives that would otherwise confound the role of information.…

Games are a simplified model of reality and often serve as a favored platform for Artificial Intelligence (AI) research. Much of the research is concerned with game-playing agents and their decision making processes. The game of Guandan…

Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a complex teacher model. However, the teacher's representations…

It is shown in recent studies that in a Stackelberg game the follower can manipulate the leader by deviating from their true best-response behavior. Such manipulations are computationally tractable and can be highly beneficial for the…

End-to-end autonomous driving has substantially progressed by directly predicting future trajectories from raw perception inputs, which bypasses traditional modular pipelines. However, mainstream methods trained via imitation learning…

With growing interest in deploying text-to-video (T2V) models in resource-constrained environments, reducing their high computational cost has become crucial, leading to extensive research on pruning and knowledge distillation methods while…

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZero takes 40 days to…