Related papers: Graph Constrained Reinforcement Learning for Natur…

Constrained multi-agent reinforcement learning offers the framework to design scalable and almost surely feasible solutions for teams of agents operating in dynamic environments to carry out conflicting tasks. We address the challenges of…

We present a generative optimization approach for learning game-playing agents, where policies are represented as Python programs and refined using large language models (LLMs). Our method treats decision-making policies as self-evolving…

This paper introduces a novel framework for modeling interacting humans in a multi-stage game. This "iterated semi network-form game" framework has the following desirable characteristics: (1) Bounded rational players, (2) strategic players…

Reinforcement Learning is a highly active research field with promising advancements. In the field of autonomous driving, however, often very simple scenarios are being examined. Common approaches use non-interpretable control commands as…

While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of…

In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to…

Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that is either positive or negative. While informative, this…

This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes…

The knowledge graph (KG) is an essential form of knowledge representation that has grown in prominence in recent years. Because it concentrates on nominal entities and their relationships, traditional knowledge graphs are static and…

Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for…

As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studies have demonstrated that Reinforcement Learning (RL) can…

Counterfactual inference is a powerful tool for analysing and evaluating autonomous agents, but its application to language model (LM) agents remains challenging. Existing work on counterfactuals in LMs has primarily focused on token-level…

Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces). In order to communicate, we flatten the complex representation of entities and their…

In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed…

Temporal knowledge graph question answering (TKGQA) aims to answer time-sensitive questions by leveraging temporal knowledge bases. While Large Language Models (LLMs) demonstrate significant potential in TKGQA, current prompting strategies…

Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a…

Text-based games present a unique class of sequential decision making problem in which agents interact with a partially observable, simulated environment via actions and observations conveyed through natural language. Such observations…

Agents in partially observable environments require persistent memory to integrate observations over time. While KGs (knowledge graphs) provide a natural representation for such evolving state, existing benchmarks rarely expose agents to…

This paper presents a game master AI for single-player role-playing games. The AI is designed to deliver interactive text-based narratives and experiences typically associated with multiplayer tabletop games like Dungeons & Dragons. We…

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven…