Human-in-the-loop Methods For Data-driven And Reinforcement Learning Systems

Abstract

Recent successes combine reinforcement learning algorithms and deep neural networks, despite reinforcement learning not being widely applied to robotics and real world scenarios. This can be attributed to the fact that current state-of-the-art, end-to-end reinforcement learning approaches still require thousands or millions of data samples to converge to a satisfactory policy and are subject to catastrophic failures during training. Conversely, in real world scenarios and after just a few data samples, humans are able to either provide demonstrations of the task, intervene to prevent catastrophic actions, or simply evaluate if the policy is performing correctly. This research investigates how to integrate these human interaction modalities to the reinforcement learning loop, increasing sample efficiency and enabling real-time reinforcement learning in robotics and real world scenarios. This novel theoretical foundation is called Cycle-of-Learning, a reference to how different human int

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygoecks2020human

Related papers

• Human-inspired Framework To Accelerate Reinforcement Learning (2023)0.00
• Human AI Interaction Loop Training: New Approach For Interactive Reinforcement Learning (2020)0.00
• Learning Shaping Strategies In Human-in-the-loop Interactive Reinforcement Learning (2018)0.00
• Real-world Human-robot Collaborative Reinforcement Learning (2020)9.41
• What Deep Reinforcement Learning Tells Us About Human Motor Learning And Vice-versa (2022)0.00
• Offline Robot Reinforcement Learning With Uncertainty-guided Human Expert Sampling (2022)0.00
• Interactive Reinforcement Learning With Dynamic Reuse Of Prior Knowledge From Human/agent's Demonstration (2018)8.60
• Perspectives On The Social Impacts Of Reinforcement Learning With Human Feedback (2023)0.00