Snapshot Reinforcement Learning: Leveraging Prior Trajectories For Efficiency

Abstract

Deep reinforcement learning (DRL) algorithms require substantial samples and computational resources to achieve higher performance, which restricts their practical application and poses challenges for further development. Given the constraint of limited resources, it is essential to leverage existing computational work (e.g., learned policies, samples) to enhance sample efficiency and reduce the computational resource consumption of DRL algorithms. Previous works to leverage existing computational work require intrusive modifications to existing algorithms and models, designed specifically for specific algorithms, lacking flexibility and universality. In this paper, we present the Snapshot Reinforcement Learning (SnapshotRL) framework, which enhances sample efficiency by simply altering environments, without making any modifications to algorithms and models. By allowing student agents to choose states in teacher trajectories as the initial state to sample, SnapshotRL can effectively ut

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhao2024snapshot

Related papers

• Prioritized Trajectory Replay: A Replay Memory For Data-driven Reinforcement Learning (2023)0.00
• Human-inspired Framework To Accelerate Reinforcement Learning (2023)0.00
• Symmetric Replay Training: Enhancing Sample Efficiency In Deep Reinforcement Learning For Combinatorial Optimization (2023)0.00
• Reverse Forward Curriculum Learning For Extreme Sample And Demonstration Efficiency In Reinforcement Learning (2024)0.00
• Reincarnating Reinforcement Learning: Reusing Prior Computation To Accelerate Progress (2022)0.00
• Deep Reinforcement Learning In A Handful Of Trials Using Probabilistic Dynamics Models (2018)0.00
• Episodic Reinforcement Learning With Expanded State-reward Space (2024)0.00
• Measuring Progress In Deep Reinforcement Learning Sample Efficiency (2021)0.00