Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be efficient and beneficial. Still, it is unclear to what extent human-AI collaboration will be successful, and how such teaming performs compared to humans or AI agents only. In this work, we show that learning from humans is effective and that human-AI collaboration outperforms human-controlled and fully autonomous AI agents in a complex simulation environment. In addition, we have developed a new simulator for critical infrastructure protection, focusing on a scenario where AI-powered drones and human teams collaborate to defend an airport against enemy drone attacks. We develop a user interface to allow humans to assist AI agents effectively. We demonstrated that agents learn faster while learning from policy correction compared to learning from humans or agents. Furthermore, human-AI collaboration requires lower mental and temporal demands, reduces human effort, and yields higher performance than if humans directly controlled all agents. In conclusion, we show that humans can provide helpful advice to the RL agents, allowing them to improve learning in a multi-agent setting.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 113 references that are in the map. First posted on arXiv 23 Dec 2023.
Builds on
36 of 113 references.
References · 36
- 2017Deep reinforcement learning from human preferencescited by 3,912
- 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
- 2017Hindsight Experience Replaycited by 1,136
- 2015Prioritized Experience Replaycited by 1,099
- 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
- 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
- 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
- 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 340
- 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 319
- 2018Reward learning from human preferences and demonstrations in Ataricited by 316
- 2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 302
- 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
24 more
- 2017Interactive Learning from Policy-Dependent Human Feedbackcited by 158
- 2017Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spacescited by 123
- 2020Learning to Utilize Shaping Rewards: A New Approach of Reward Shapingcited by 114
- 2022SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learningcited by 97
- 2020Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferencescited by 71
- 2019Learning Reward Functions by Integrating Human Demonstrations and Preferencescited by 64
- 2022Reward Uncertainty for Exploration in Preference-based Reinforcement Learningcited by 61
- 2020Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learningcited by 57
- 2019Deep Reinforcement Learning from Policy-Dependent Human Feedbackcited by 56
- 2016Q(λ) with Off-Policy Correctionscited by 48
- 2018DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedbackcited by 41
- 2020Learning Rewards from Linguistic Feedbackcited by 41
- 2020Constrained Markov Decision Processes via Backward Value Functionscited by 33
- 2023Reinforcement Learning from Diverse Human Preferencescited by 24
- 2019On the Utility of Model Learning in HRIcited by 21
- 2020A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Reviewcited by 15
- 2019Improving Deep Reinforcement Learning in Minecraft with Action Advicecited by 10
- 2020Maximum Reward Formulation In Reinforcement Learningcited by 10
- 2021Action Advising with Advice Imitation in Deep Reinforcement Learningcited by 10
- 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Drivingcited by 7
- 2021Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operationscited by 3
- 2021Off-Policy Correction For Multi-Agent Reinforcement Learningcited by 2
- 2022Learning Action Duration and Synergy in Task Planning for Human-Robot Collaborationcited by 2
- 2020Computing Diverse Sets of Solutions for Monotone Submodular Optimisation Problemscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.