Backplay: "man Muss Immer Umkehren"

Abstract

Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our approach, Backplay, uses a single demonstration to construct a curriculum for a given task. Rather than starting each training episode in the environment's fixed initial state, we start the agent near the end of the demonstration and move the starting point backwards during the course of training until we reach the initial state. Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency. This includes reward shaping, behavioral cloning, and reverse curriculum g

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyresnick2018backplay

Related papers

• Reverse Forward Curriculum Learning For Extreme Sample And Demonstration Efficiency In Reinforcement Learning (2024)0.00
• Barc: Backward Reachability Curriculum For Robotic Reinforcement Learning (2018)10.74
• Generating Automatic Curricula Via Self-supervised Active Domain Randomization (2020)0.00
• Task Phasing: Automated Curriculum Learning From Demonstrations (2022)5.24
• Replay For Safety (2021)0.00
• Backward Curriculum Reinforcement Learning (2022)0.00
• Forward-backward Reinforcement Learning (2018)0.00
• Symmetric Replay Training: Enhancing Sample Efficiency In Deep Reinforcement Learning For Combinatorial Optimization (2023)0.00