JAXtari is an open‑source, high‑performance reimplementation of Atari 2600 environments that enables massive GPU parallelization. It allows PPO agents to complete 100 M environment steps on a single A100‑GPU in under an hour, far faster than the CPU‑based ALE. Additionally, JAXtari provides object‑centric observations and a flexible modification system, facilitating research into causal modeling, neuro‑symbolic methods, and rapid agent adaptation.
arXiv:2510. 01764v3 Announce Type: replace Abstract: Reinforcement learning (RL) research requires diverse, challenging environments that are both tractable and scalable.
Wayfarer is a domain‑agnostic, online deep RL agent that discovers options via Laplacian representation learning from high‑dimensional observations and uses them for control. The discovered options improve exploration, accelerate credit assignment, and generalise to unseen settings, leading to faster learning of complex policies. Wayfarer achieves state‑of‑the‑art performance among single‑stream agents on the most challenging Atari 2600 games, especially those requiring long‑horizon exploration such as Montezuma's Revenge and Private Eye.
arXiv:2606. 19357v1 Announce Type: cross Abstract: We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen.
arXiv:2410.14606v3 Announce Type: replace Abstract: Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streami...
arXiv:2608. 16798v1 Announce Type: cross Abstract: Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment.
arXiv:2609.09059v1 Announce Type: new Abstract: While many video-game environments (VGEs) have played crucial roles in advancing reinforcement learning (RL), developing novel VGEs or modifying existi...
MAI-Gym is an open, all-in-one platform that unifies GUI agent evaluation, data collection, and online reinforcement learning training across mobile, computer, and web environments. It supports ten established benchmarks, scales to 20,000 parallel environment instances, and enables automated synthesis of diverse GUI applications and tasks with execution-validated verifiers. Using this platform, the authors trained a 9B-parameter agent, MAI-Gym-9B, achieving state‑of‑the‑art performance on MobileWorld and OSWorld-Verified, and demonstrated that training on a mocked train‑ticketing app improves real‑world task success from 28.8% to 48.1% on a physical phone.
BluffJAX is an open‑source suite of adversarial imperfect‑information games implemented in JAX, designed for high‑throughput simulation and GPU parallelization. It includes classic benchmarks like Texas Hold’Em and Kuhn Poker, as well as newer games such as Bluff, Stud Poker, and Kemps, aiming to broaden research in game‑theoretic reinforcement learning. The authors benchmarked throughput, memory usage, and algorithmic performance across single and multi‑GPU setups, showing scalability to hundreds of millions of samples per second and providing baseline results for future work.
arXiv:2610.20584v1 Announce Type: new Abstract: Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their...
LoongSage is a lightweight, fully asynchronous reinforcement learning framework designed for large language models that perform agentic tasks. It integrates with Megatron for distributed training and SGLang for high‑throughput inference, centralizing orchestration in a single controller and using Ray actors for GPU components. The framework introduces AgentFlow for unified execution of white‑box and black‑box agents, sliding‑window strategies to limit trajectory staleness, TransferMesh for efficient weight synchronization, and a memory‑efficient Teacher Manager that supports multi‑teacher on‑policy distillation. Experiments across four training runs show steady reward improvement, controlled train‑inference gaps, and sustained hardware utilization by eliminating synchronous idle periods.
arXiv:2609.13243v1 Announce Type: cross Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprod...
arXiv:2609.38733v1 Announce Type: new Abstract: Recent LLM-based approaches to control either invoke a language model to select actions or synthesize world models that require planning at every decis...