Deep Reinforcement Learning (DRL) has achieved remarkable success in complex sequential decision-making tasks, such as playing Atari 2600 games and mastering board games. A critical yet underexplored aspect of DRL is the temporal scale of action execution. We propose a novel paradigm that integrates contextual bandits with DRL to adaptively select action durations, enhancing policy flexibility and computational efficiency. Our approach augments a Deep Q-Network (DQN) with a contextual bandit module that learns to choose optimal action repetition rates based on state contexts. Experiments on Atari 2600 games demonstrate significant performance improvements over static duration baselines, highlighting the efficacy of adaptive temporal abstractions in DRL. This paradigm offers a scalable solution for real-time applications like gaming and robotics, where dynamic action durations are critical.
Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that help them on downstream tasks but also may notoriously sway their outputs towards wrong or biased answers. In this work, we test how the knowledge about popular subjects hurt the accuracy of vision language models (VLMs) on standard, objective visual tasks of counting and identification. We find that state-of-the-art VLMs are strongly biased (e.g, unable to recognize a fourth stripe has been added to a 3-stripe Adidas logo) scoring an average of 17.05% accuracy in counting (e.g., counting stripes in an Adidas-like logo) across 7 diverse domains from animals, logos, chess, board games, optical illusions, to patterned grids. Insert text (e.g., "Adidas") describing the subject name into the counterfactual image further decreases VLM accuracy. The biases in VLMs are so strong that instructing them to double-check their results or rely exclusively on image details to answer improves counting accuracy by only +2 points, on average. Our work presents an interesting failure mode in VLMs and an automated framework for testing VLM biases. Code and data are available at: vlmsarebiased.github.io.
Large Language Models (LLMs) have demonstrated strong performance on tasks with short time frames, but struggle with tasks requiring longer durations. While datasets covering extended-duration tasks, such as software engineering tasks or video games, do exist, there are currently few implementations of complex board games specifically designed for reinforcement learning and LLM evaluation. To address this gap, we propose the 4Hammer reinforcement learning environment, a digital twin simulation of a subset of Warhammer 40,000-a complex, zero-sum board game. Warhammer 40,000 features intricate rules, requiring human players to thoroughly read and understand over 50 pages of detailed natural language rules, grasp the interactions between their game pieces and those of their opponents, and independently track and communicate the evolving game state.
Significant progress has been made in AI for games, including board games, MOBA, and RTS games. However, complex agents are typically developed in an embedded manner, directly accessing game state information, unlike human players who rely on noisy visual data, leading to unfair competition. Developing complex non-embedded agents remains challenging, especially in card-based RTS games with complex features and large state spaces. We propose a non-embedded offline reinforcement learning training strategy using visual inputs to achieve real-time autonomous gameplay in the RTS game Clash Royale. Due to the lack of a object detection dataset for this game, we designed an efficient generative object detection dataset for training. We extract features using state-of-the-art object detection and optical character recognition models. Our method enables real-time image acquisition, perception feature fusion, decision-making, and control on mobile devices, successfully defeating built-in AI opponents. All code is open-sourced at https://github.com/wty-yy/katacr.
We introduce ZeroSumEval, a dynamic, competition-based, and evolving evaluation framework for Large Language Models (LLMs) that leverages competitive games. ZeroSumEval encompasses a diverse suite of games, including security challenges (Capture the Flag), classic board games (chess), and knowledge tests (MathQuiz). These games are designed to evaluate a range of capabilities such as strategic reasoning, planning, knowledge application, safety, and adaptability. Building upon recent studies that highlight the effectiveness of game-based evaluations for LLMs, ZeroSumEval enhances these approaches by providing a standardized and extensible framework for easily implementing games and leverages DSPy to provide a better abstraction for LLM player strategies.
Hex and Counter Wargames are adversarial two-player simulations of real military conflicts requiring complex strategic decision-making. Unlike classical board games, these games feature intricate terrain/unit interactions, unit stacking, large maps of varying sizes, and simultaneous move and combat decisions involving hundreds of units. This paper introduces a novel system designed to address the strategic complexity of Hex and Counter Wargames by integrating cutting-edge advancements in Recurrent Neural Networks with AlphaZero, a reliable modern Reinforcement Learning algorithm. The system utilizes a new Neural Network architecture developed from existing research, incorporating innovative state and action representations tailored to these specific game environments. With minimal training, our solution has shown promising results in typical scenarios, demonstrating the ability to generalize across different terrain and tactical situations. Additionally, we explore the system's potential to scale to larger map sizes. The developed system is openly accessible, facilitating continued research and exploration within this challenging domain.
Neural scaling laws are observed in a range of domains, to date with no clear understanding of why they occur. Recent theories suggest that loss power laws arise from Zipf's law, a power law observed in domains like natural language. One theory suggests that language scaling laws emerge when Zipf-distributed task quanta are learned in descending order of frequency. In this paper we examine power-law scaling in AlphaZero, a reinforcement learning algorithm, using a theory of language-model scaling. We find that game states in training and inference data scale with Zipf's law, which is known to arise from the tree structure of the environment, and examine the correlation between scaling-law and Zipf's-law exponents. In agreement with quanta scaling theory, we find that agents optimize state loss in descending order of frequency, even though this order scales inversely with modelling complexity. We also find that inverse scaling, the failure of models to improve with size, is correlated with unusual Zipf curves where end-game states are among the most frequent states. We show evidence that larger models shift their focus to these less-important states, sacrificing their understanding of important early-game states.
This paper presents novel game-playing AI agents based on the AlphaZero framework, enhanced with Vision Transformer (ViT): AlphaViT, AlphaViD, and AlphaVDA. These agents are designed to play multiple board games of various sizes using a single network with shared weights, thereby overcoming AlphaZero's limitation of fixed-board-size constraints. AlphaViT employs only a transformer encoder, whereas AlphaViD and AlphaVDA incorporate both transformer encoders and decoders. In AlphaViD, the decoder processes outputs from the encoder, whereas AlphaVDA uses a learnable embeddings as the decoder input. The additional decoder layers in AlphaViD and AlphaVDA provide flexibility to adapt to various action spaces and board sizes. Experimental results show that the proposed agents, trained on either individual games or multiple games simultaneously, consistently outperform traditional algorithms such as Minimax and Monte Carlo Tree Search and approach the performance of AlphaZero, despite using a single deep neural network (DNN) with shared weights. In particular, AlphaViT shows strong performance across all tested games. Furthermore, fine-tuning the DNN using pre-trained weights from small-board games accelerates convergence and improves performance, particularly in Gomoku. Interestingly, simultaneous training on multiple games yields performance comparable to, or even surpassing, single-game training. These results indicate the potential of transformer-based architectures to develop more flexible and robust game-playing AI agents that excel in multiple games and dynamic environments.
Defining and measuring decision-making styles, also known as playstyles, is crucial in gaming, where these styles reflect a broad spectrum of individuality and diversity. However, finding a universally applicable measure for these styles poses a challenge. Building on Playstyle Distance, the first unsupervised metric to measure playstyle similarity based on game screens and raw actions, we introduce three enhancements to increase accuracy: multiscale analysis with varied state granularity, a perceptual kernel rooted in psychology, and the utilization of the intersection-over-union method for efficient evaluation. These innovations not only advance measurement precision but also offer insights into human cognition of similarity. Across two racing games and seven Atari games, our techniques significantly improve the precision of zero-shot playstyle classification, achieving an accuracy exceeding 90 percent with fewer than 512 observation-action pairs, which is less than half an episode of these games. Furthermore, our experiments with 2048 and Go demonstrate the potential of discrete playstyle measures in puzzle and board games. We also develop an algorithm for assessing decision-making diversity using these measures. Our findings improve the measurement of end-to-end game analysis and the evolution of artificial intelligence for diverse playstyles.
Reinforcement learning (RL) has progressed substantially over the past decade, with much of this progress being driven by benchmarks. Many benchmarks are focused on video or board games, and a large number of robotics benchmarks lack diversity and real-world applicability. In this paper, we aim to simplify the process of applying reinforcement learning in the 3D simulation league of Robocup, a robotic football competition. To this end, we introduce a Robocup-based RL environment based on the open source rcssserver3d soccer server, simple pre-defined tasks, and integration with a popular RL library, Stable Baselines 3. Our environment enables the creation of high-dimensional continuous control tasks within a robotics football simulation. In each task, an RL agent controls a simulated Nao robot, and can interact with the ball or other agents. We open-source our environment and training code at https://github.com/Michael-Beukman/RobocupGym.
Automatically generating novel and interesting games is a complex task. Challenges include representing game rules in a computationally workable form, searching through the large space of potential games under most such representations, and accurately evaluating the originality and quality of previously unseen games. Prior work in automated game generation has largely focused on relatively restricted rule representations and relied on domain-specific heuristics. In this work, we explore the generation of novel games in the comparatively expansive Ludii game description language, which encodes the rules of over 1000 board games in a variety of styles and modes of play. We draw inspiration from recent advances in large language models and evolutionary computation in order to train a model that intelligently mutates and recombines games and mechanics expressed as code. We demonstrate both quantitatively and qualitatively that our approach is capable of generating new and interesting games, including in regions of the potential rules space not covered by existing games in the Ludii dataset. A sample of the generated games are available to play online through the Ludii portal.
Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an auxiliary pessimistic model, updated adversarially, to estimate the worst-case MDP within a Kullback-Leibler uncertainty set. In comparison to several existing works, our work does not impose any additional conditions on the training environment, such as the need for a parametric simulator. To test the effectiveness of the proposed pessimistic model in enhancing policy robustness, we integrate it into a practical RL algorithm, called Robust Model-Based Policy Optimization (RMBPO). Our experimental results indicate a notable improvement in policy robustness on high-dimensional MuJoCo control tasks, with the auxiliary model enhancing the performance of the learned policy in distorted MDPs. We further explore the learned deviation between the proposed auxiliary world model and the nominal model, to examine how pessimism is achieved. By learning a pessimistic world model and demonstrating its role in improving policy robustness, our research contributes towards making (model-based) RL more robust.
Games, including abstract board games, constitute a convenient ground to create, design, and improve new AI methods. In this field, Monte Carlo Tree Search is a popular algorithm family, aiming to build game trees and explore them efficiently. Combinatorial Optimization, on the other hand, aims to model and solve problems with an objective to optimize and constraints to satisfy, and is less common in Game AI. We believe however that both methods can be combined efficiently, by injecting Combinatorial Optimization into Monte Carlo Tree Search to help the tree search, leading to a novel combination of these two techniques. Tested on the board game boop., our method beats 96% of the time the Monte Carlo Tree Search algorithm baseline. We conducted an ablation study to isolate and analyze which injections and combinations of injections lead to such performances. Finally, we opposed our AI method against human players on the Board Game Arena platform, and reached a 373 ELO rating after 51 boop. games, with a 69% win rate and finishing ranked 56th worldwide on the platform over 5,316 boop. players.
This paper introduces a novel algorithm for two-player deterministic games with perfect information, which we call PROBS (Predict Results of Beam Search). Unlike existing methods that predominantly rely on Monte Carlo Tree Search (MCTS) for decision processes, our approach leverages a simpler beam search algorithm. We evaluate the performance of our algorithm across a selection of board games, where it consistently demonstrates an increased winning ratio against baseline opponents. A key result of this study is that the PROBS algorithm operates effectively, even when the beam search size is considerably smaller than the average number of turns in the game.
Monte Carlo Tree Search (MCTS)-based algorithms, such as MuZero and its derivatives, have achieved widespread success in various decision-making domains. These algorithms employ the reanalyze process to enhance sample efficiency from stale data, albeit at the expense of significant wall-clock time consumption. To address this issue, we propose a general approach named ReZero to boost tree search operations for MCTS-based algorithms. Specifically, drawing inspiration from the one-armed bandit model, we reanalyze training samples through a backward-view reuse technique which uses the value estimation of a certain child node to save the corresponding sub-tree search time. To further adapt to this design, we periodically reanalyze the entire buffer instead of frequently reanalyzing the mini-batch. The synergy of these two designs can significantly reduce the search cost and meanwhile guarantee or even improve performance, simplifying both data collecting and reanalyzing. Experiments conducted on Atari environments, DMControl suites and board games demonstrate that ReZero substantially improves training speed while maintaining high sample efficiency. The code is available as part of the LightZero MCTS benchmark at https://github.com/opendilab/LightZero.
The use of generative AI in education is a controversial topic. Current technology offers the potential to create educational content from text, speech, to images based on simple input prompts. This can enhance productivity by summarizing knowledge and improving communication, quickly adjusting to different types of learners. Moreover, generative AI holds the promise of making the learning itself more fun, by responding to user inputs and dynamically generating high-quality creative material. In this paper we present the multisensory educational game ArchiGuesser that combines various AI technologies from large language models, image generation, to computer vision to serve a single purpose: Teaching students in a playful way the diversity of our architectural history and how generative AI works.
Building agents based on tree-search planning capabilities with learned models has achieved remarkable success in classic decision-making problems, such as Go and Atari. However, it has been deemed challenging or even infeasible to extend Monte Carlo Tree Search (MCTS) based algorithms to diverse real-world applications, especially when these environments involve complex action spaces and significant simulation costs, or inherent stochasticity. In this work, we introduce LightZero, the first unified benchmark for deploying MCTS/MuZero in general sequential decision scenarios. Specificially, we summarize the most critical challenges in designing a general MCTS-style decision-making solver, then decompose the tightly-coupled algorithm and system design of tree-search RL methods into distinct sub-modules. By incorporating more appropriate exploration and optimization strategies, we can significantly enhance these sub-modules and construct powerful LightZero agents to tackle tasks across a wide range of domains, such as board games, Atari, MuJoCo, MiniGrid and GoBigger. Detailed benchmark results reveal the significant potential of such methods in building scalable and efficient decision intelligence. The code is available as part of OpenDILab at https://github.com/opendilab/LightZero.
Game solving is a similar, yet more difficult task than mastering a game. Solving a game typically means to find the game-theoretic value (outcome given optimal play), and optionally a full strategy to follow in order to achieve that outcome. The AlphaZero algorithm has demonstrated super-human level play, and its powerful policy and value predictions have also served as heuristics in game solving. However, to solve a game and obtain a full strategy, a winning response must be found for all possible moves by the losing player. This includes very poor lines of play from the losing side, for which the AlphaZero self-play process will not encounter. AlphaZero-based heuristics can be highly inaccurate when evaluating these out-of-distribution positions, which occur throughout the entire search. To address this issue, this paper investigates applying online fine-tuning while searching and proposes two methods to learn tailor-designed heuristics for game solving. Our experiments show that using online fine-tuning can solve a series of challenging 7x7 Killall-Go problems, using only 23.54% of computation time compared to the baseline without online fine-tuning. Results suggest that the savings scale with problem size. Our method can further be extended to any tree search algorithm for problem solving. Our code is available at https://rlg.iis.sinica.edu.tw/papers/neurips2023-online-fine-tuning-solver.
The gameplay of strategic board games such as chess, Go and Hex is often characterized by combinatorial, relational structures -- capturing distinct interactions and non-local patterns -- and not just images. Nonetheless, most common self-play reinforcement learning (RL) approaches simply approximate policy and value functions using convolutional neural networks (CNN). A key feature of CNNs is their relational inductive bias towards locality and translational invariance. In contrast, graph neural networks (GNN) can encode more complicated and distinct relational structures. Hence, we investigate the crucial question: Can GNNs, with their ability to encode complex connections, replace CNNs in self-play reinforcement learning? To this end, we do a comparison with Hex -- an abstract yet strategically rich board game -- serving as our experimental platform. Our findings reveal that GNNs excel at dealing with long range dependency situations in game states and are less prone to overfitting, but also showing a reduced proficiency in discerning local patterns. This suggests a potential paradigm shift, signaling the use of game-specific structures to reshape self-play reinforcement learning.
Board games are a great source of entertainment for all ages, as they create a competitive and engaging environment, as well as stimulating learning and strategic thinking. It is common for digital versions of board games, as any other type of digital games, to offer the option to select the difficulty of the game. This is usually done by customizing the search parameters of the AI algorithm. However, this approach cannot be extended to General Game Playing agents, as different games might require different parametrization for each difficulty level. In this paper, we present a general approach to implement an artificial intelligence opponent with difficulty levels for zero-sum games, together with a propose of a Minimax-MCTS hybrid algorithm, which combines the minimax search process with GGP aspects of MCTS. This approach was tested in our mobile application LoBoGames, an extensible board games platform, that is intended to have an broad catalog of games, with an emphasis on accessibility: the platform is friendly to visually-impaired users, and is compatible with more than 92\% of Android devices. The tests in this work indicate that both the hybrid Minimax-MCTS and the new difficulty adjustment system are promising GGP approaches that could be expanded in future work.