GameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games
cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/baekalfen/pyboy
Project page: https://dhananjayashok.github.io/GameBoyWorlds-Benchmark/1
Terminology
Sources
- Qwen3-VL Technical Report
- RT-H: Action Hierarchies Using Language
- Exploration by Random Network Distillation
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
- Mastering Atari with Discrete World Models
- LoRA: Low-Rank Adaptation of Large Language Models
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Continual Harness: Online Adaptation for Self-Improving Foundation Agents
- Playing Atari with Deep Reinforcement Learning
- GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
- Proximal Policy Optimization Algorithms
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- OpenAI GPT-5 System Card
- StarCraft II: A New Challenge for Reinforcement Learning
- VideoGameBench: Can Vision-Language Models complete popular video games?
- Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection