Reverse Forward Curriculum Learning For Extreme Sample And Demonstration Efficiency In Reinforcement Learning

Abstract

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data that is difficult to obtain, especially for domains such as robotics. Our approach consists of a reverse curriculum followed by a forward curriculum. Unique to our approach compared to past work is the ability to efficiently leverage more than one demonstration via a per-demonstration reverse curriculum generated via state resets. The result of our reverse curriculum is an initial policy that performs well on a narrow initial state distribution and helps overcome difficult exploration problems. A forward curriculum is then used to accelerate the training of the initial policy to perform well on the full initial state distribu

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytao2024reverse

Related papers

• Backplay: "man Muss Immer Umkehren" (2018)0.00
• Barc: Backward Reachability Curriculum For Robotic Reinforcement Learning (2018)10.74
• AWAC: Accelerating Online Reinforcement Learning With Offline Datasets (2020)0.00
• Backward Curriculum Reinforcement Learning (2022)0.00
• Task Phasing: Automated Curriculum Learning From Demonstrations (2022)5.24
• Human-inspired Framework To Accelerate Reinforcement Learning (2023)0.00
• Enhancing Offline Reinforcement Learning With Curriculum Learning-based Trajectory Valuation (2025)0.00
• Guided Online Distillation: Promoting Safe Reinforcement Learning By Offline Demonstration (2023)4.52