Interactive Reinforcement Learning With Dynamic Reuse Of Prior Knowledge From Human/agent's Demonstration

Abstract

Reinforcement learning has enjoyed multiple successes in recent years. However, these successes typically require very large amounts of data before an agent achieves acceptable performance. This paper introduces a novel way of combating such requirements by leveraging existing (human or agent) knowledge. In particular, this paper uses demonstrations from agents and humans, allowing an untrained agent to quickly achieve high performance. We empirically compare with, and highlight the weakness of, HAT and CHAT, methods of transferring knowledge from a source agent/human to a target agent. This paper introduces an effective transfer approach, DRoP, combining the offline knowledge (demonstrations recorded before learning) with online confidence-based performance analysis. DRoP dynamically involves the demonstrator's knowledge, integrating it into the reinforcement learning agent's online learning loop to achieve efficient and robust learning.

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keywang2018interactive

Related papers

• Demonstration-guided Continual Reinforcement Learning In Dynamic Environments (2025)0.00
• Knowru: Knowledge Reusing Via Knowledge Distillation In Multi-agent Reinforcement Learning (2021)9.23
• Psiphi-learning: Reinforcement Learning With Demonstrations Using Successor Features And Inverse Temporal Difference Learning (2021)0.00
• Efficient Open-world Reinforcement Learning Via Knowledge Distillation And Autonomous Rule Discovery (2023)0.00
• Human-inspired Framework To Accelerate Reinforcement Learning (2023)0.00
• Reverse Forward Curriculum Learning For Extreme Sample And Demonstration Efficiency In Reinforcement Learning (2024)0.00
• Learning From Demonstrations With SACR2: Soft Actor-critic With Reward Relabeling (2021)0.00
• Improved Reinforcement Learning In Cooperative Multi-agent Environments Using Knowledge Transfer (2021)0.00