L2explorer: A Lifelong Reinforcement Learning Assessment Environment

Abstract

Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolving, open-world problems often found in critical application spaces. Reinforcement learning solutions tend to generalize poorly when exposed to new tasks outside of the data distribution they are trained on, prompting an interest in continual learning algorithms. In tandem with research on continual learning algorithms, there is a need for challenge environments, carefully designed experiments, and metrics to assess research progress. We address the latter need by introducing a framework for continual reinforcement-learning development and assessment using Lifelong Learning Explorer (L2Explorer), a new, Unity-based, first-person 3D exploration environment that can be continuously reconfigured to generate a range of tasks and task variants structured into complex and evolving evaluation curricula. In contrast

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjohnson2022l2explorer

Related papers

• Reactive Exploration To Cope With Non-stationarity In Lifelong Reinforcement Learning (2022)0.00
• Continuous Coordination As A Realistic Scenario For Lifelong Learning (2021)0.00
• A Survey On Enhancing Reinforcement Learning In Complex Environments: Insights From Human And LLM Feedback (2024)0.00
• Eden: A Unified Environment Framework For Booming Reinforcement Learning Algorithms (2021)0.00
• Go-explore: A New Approach For Hard-exploration Problems (2019)0.00
• Learning Curricula In Open-ended Worlds (2023)0.00
• Rlexplore: Accelerating Research In Intrinsically-motivated Reinforcement Learning (2024)5.33
• Continual Reinforcement Learning In 3D Non-stationary Environments (2019)0.00