相关论文: Agent57: Outperforming the Atari Human Benchmark

This paper presents a novel approach to automated playtesting for the prediction of human player behavior and experience. It has previously been demonstrated that Deep Reinforcement Learning (DRL) game-playing agents can predict both game…

Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning…

Recent large language models (LLMs) have demonstrated great potential toward intelligent agents and next-gen automation, but there currently lacks a systematic benchmark for evaluating LLMs' abilities as agents. We introduce SmartPlay: both…

Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data,…

In this work, we study two self-play training schemes, Chainer and Pool, and show they lead to improved agent performance in Atari Pong compared to a standard DQN agent -- trained against the built-in Atari opponent. To measure agent…

The rapid rise of large language models (LLMs) has shifted artificial intelligence (AI) research toward agentic systems, motivating the use of weaker and more flexible notions of agency. However, this shift raises key questions about the…

Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are…

In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time. We have developed a…

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The…

Agent-based Models (ABMs) are valuable tools for policy analysis. ABMs help analysts explore the emergent consequences of policy interventions in multi-agent decision-making settings. But the validity of inferences drawn from ABM…

We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like…

Reinforcement learning has enabled agents to solve challenging tasks in unknown environments. However, manually crafting reward functions can be time consuming, expensive, and error prone to human error. Competing objectives have been…

For over a decade now, robotics and the use of artificial agents have become a common thing.Testing the performance of new path finding or search space optimization algorithms has also become a challenge as they require simulation or an…

Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable…

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or…

Learning an effective representation for high-dimensional data is a challenging problem in reinforcement learning (RL). Deep reinforcement learning (DRL) such as Deep Q networks (DQN) achieves remarkable success in computer games by…

Recent advances in reinforcement learning (RL) heavily rely on a variety of well-designed benchmarks, which provide environmental platforms and consistent criteria to evaluate existing and novel algorithms. Specifically, in multi-agent RL…

AI agents, empowered by Large Language Models (LLMs) and communication protocols such as MCP and A2A, have rapidly evolved from simple chatbots to autonomous entities capable of executing complex, multi-step tasks, demonstrating great…

Reinforcement learning (RL) has been demonstrated suitable to develop agents that play complex games with human-level performance. However, it is not understood how to effectively use RL to perform cybersecurity tasks. To develop such…

Deep Reinforcement Learning (DRL) agents frequently face challenges in adapting to tasks outside their training distribution, including issues with over-fitting, catastrophic forgetting and sample inefficiency. Although the application of…