Recent advancements in Large Language Models(LLMs) have led to the development of LLM-based AI agents. A key challenge is the creation of agents that can effectively ground themselves in complex, adversarial long-horizon environments. Existing methods mainly focus on (1) using LLMs as policies to interact with the environment through generating low-level feasible actions, and (2) utilizing LLMs to generate high-level tasks or language guides to stimulate action generation. However, the former struggles to generate reliable actions, while the latter relies heavily on expert experience to translate high-level tasks into specific action sequences. To address these challenges, we introduce the Plan with Language, Act with Parameter (PLAP) planning framework that facilitates the grounding of LLM-based agents in long-horizon environments. The PLAP method comprises three key components: (1) a skill library containing environment-specific parameterized skills, (2) a skill planner powered by LLMs, and (3) a skill executor converting the parameterized skills into executable action sequences. We implement PLAP in MicroRTS, a long-horizon real-time strategy game that provides an unfamiliar and challenging environment for LLMs. The experimental results demonstrate the effectiveness of PLAP. In particular, GPT-4o-driven PLAP in a zero-shot setting outperforms 80% of baseline agents, and Qwen2-72B-driven PLAP, with carefully crafted few-shot examples, surpasses the top-tier scripted agent, CoacAI. Additionally, we design comprehensive evaluation metrics and test 6 closed-source and 2 open-source LLMs within the PLAP framework, ultimately releasing an LLM leaderboard ranking long-horizon skill planning ability. Our code is available at https://github.com/AI-Research-TeamX/PLAP.

Play style identification can provide valuable game design insights and enable adaptive experiences, with the potential to improve game playing agents. Previous work relies on domain knowledge to construct play trace representations using handcrafted features. More recent approaches incorporate the sequential structure of play traces but still require some level of domain abstraction. In this study, we explore the use of unsupervised CNN-LSTM autoencoder models to obtain latent representations directly from low-level play trace data in MicroRTS. We demonstrate that this approach yields a meaningful separation of different game playing agents in the latent space, reducing reliance on domain expertise and its associated biases. This latent space is then used to guide the exploration of diverse play styles within studied AI players.

Outside of transfer learning settings, reinforcement learning agents start their learning process from a clean slate. As a result, such agents have to go through a slow process to learn even the most obvious skills required to solve a problem. In this paper, we present InnateCoder, a system that leverages human knowledge encoded in foundation models to provide programmatic policies that encode "innate skills" in the form of temporally extended actions, or options. In contrast to existing approaches to learning options, InnateCoder learns them from the general human knowledge encoded in foundation models in a zero-shot setting, and not from the knowledge the agent gains by interacting with the environment. Then, InnateCoder searches for a programmatic policy by combining the programs encoding these options into larger and more complex programs. We hypothesized that InnateCoder's way of learning and using options could improve the sampling efficiency of current methods for learning programmatic policies. Empirical results in MicroRTS and Karel the Robot support our hypothesis, since they show that InnateCoder is more sample efficient than versions of the system that do not use options or learn them from experience.

Syntax-guided synthesis is commonly used to generate programs encoding policies. In this approach, the set of programs, that can be written in a domain-specific language defines the search space, and an algorithm searches within this space for programs that encode strong policies. In this paper, we propose an alternative method for synthesizing programmatic policies, where we search within an approximation of the language's semantic space. We hypothesized that searching in semantic spaces is more sample-efficient compared to syntax-based spaces. Our rationale is that the search is more efficient if the algorithm evaluates different agent behaviors as it searches through the space, a feature often missing in syntax-based spaces. This is because small changes in the syntax of a program often do not result in different agent behaviors. We define semantic spaces by learning a library of programs that present different agent behaviors. Then, we approximate the semantic space by defining a neighborhood function for local search algorithms, where we replace parts of the current candidate program with programs from the library. We evaluated our hypothesis in a real-time strategy game called MicroRTS. Empirical results support our hypothesis that searching in semantic spaces can be more sample-efficient than searching in syntax-based spaces.

This paper introduces Local Learner (2L), an algorithm for providing a set of reference strategies to guide the search for programmatic strategies in two-player zero-sum games. Previous learning algorithms, such as Iterated Best Response (IBR), Fictitious Play (FP), and Double-Oracle (DO), can be computationally expensive or miss important information for guiding search algorithms. 2L actively selects a set of reference strategies to improve the search signal. We empirically demonstrate the advantages of our approach while guiding a local search algorithm for synthesizing strategies in three games, including MicroRTS, a challenging real-time strategy game. Results show that 2L learns reference strategies that provide a stronger search signal than IBR, FP, and DO. We also simulate a tournament of MicroRTS, where a synthesizer using 2L outperformed the winners of the two latest MicroRTS competitions, which were programmatic strategies written by human programmers.

This paper presents a preliminary study comparing different observation and action space representations for Deep Reinforcement Learning (DRL) in the context of Real-time Strategy (RTS) games. Specifically, we compare two representations: (1) a global representation where the observation represents the whole game state, and the RL agent needs to choose which unit to issue actions to, and which actions to execute; and (2) a local representation where the observation is represented from the point of view of an individual unit, and the RL agent picks actions for each unit independently. We evaluate these representations in MicroRTS showing that the local representation seems to outperform the global representation when training agents with the task of harvesting resources.