相关论文: Pgx: Hardware-Accelerated Parallel Game Simulators…

Deep reinforcement learning (RL) is a powerful framework to train decision-making models in complex environments. However, RL can be slow as it requires repeated interaction with a simulation of the environment. In particular, there are key…

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,…

Stochastic simulation techniques employed for the analysis of portfolios of insurance/reinsurance risk, often referred to as `Aggregate Risk Analysis', can benefit from exploiting state-of-the-art high-performance computing platforms. In…

Deep reinforcement learning (DRL) has revolutionized learning and actuation in applications such as game playing and robotic control. The cost of data collection, i.e., generating transitions from agent-environment interactions, remains a…

In recent years, \emph{Reinforcement Learning} (RL) has made remarkable progress, achieving superhuman performance in a wide range of simulated environments. As research moves toward deploying RL in real-world applications, the field faces…

We introduce a real-time strategy game environment based on Generals.io, a game with thousands of weekly active players. Our environment is fully compatible with Gymnasium and PettingZoo and is capable of running thousands of frames per…

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to the vast…

Reinforcement learning has been demonstrated to outperform even the best humans in complex domains like video games. However, running reinforcement learning experiments on the required scale for autonomous driving is extremely difficult.…

Reinforcement learning (RL) -- algorithms that teach artificial agents to interact with environments by maximising reward signals -- has achieved significant success in recent years. These successes have been facilitated by advances in…

Nowadays, realistic simulation environments are essential to validate and build reliable robotic solutions. This is particularly true when using Reinforcement Learning (RL) based control policies. To this end, both robotics and RL…

In this paper, we propose Rogue-Gym, a simple and classic style roguelike game built for evaluating generalization in reinforcement learning (RL). Combined with the recent progress of deep neural networks, RL has successfully trained…

Mechanical search (MS) in cluttered environments remains a significant challenge for autonomous manipulators, requiring long-horizon planning and robust state estimation under occlusions and partial observability. In this work, we introduce…

Robotic surgery is a rapidly developing field that can greatly benefit from the automation of surgical tasks. However, training techniques such as Reinforcement Learning (RL) require a high number of task repetitions, which are generally…

Reinforcement learning with verifiable rewards (RLVR) has recently unlocked strong reasoning capabilities in large language models (LLMs), triggering rapid exploration of new algorithms and data. However, RLVR training is notoriously…

We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradient-based loss minimization and uses projection operators and iterative projection algorithms.…

Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges such as sample inefficiency and unstable learning dynamics.…

Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…

We propose a new benchmark environment for evaluating Reinforcement Learning (RL) algorithms: the PlayStation Learning Environment (PSXLE), a PlayStation emulator modified to expose a simple control API that enables rich game-state…

This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning (RL) with large sequence models (such as transformers). With such models, existing systems such as Reverb…

We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased…