Corpus ID: 1301081

Agent-Agnostic Human-in-the-Loop Reinforcement Learning

@article{Abel2017AgentAgnosticHR,
  title={Agent-Agnostic Human-in-the-Loop Reinforcement Learning},
  author={David Abel and J. Salvatier and Andreas Stuhlm{\"u}ller and Owain Evans},
  journal={ArXiv},
  year={2017},
  volume={abs/1701.04079}
}
  • David Abel, J. Salvatier, +1 author Owain Evans
  • Published 2017
  • Computer Science
  • ArXiv
  • Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher's guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop… CONTINUE READING
    28 Citations

    Figures and Topics from this paper.

    Learning Shaping Strategies in Human-in-the-loop Interactive Reinforcement Learning
    • 1
    • Highly Influenced
    • PDF
    Learning from Human Feedback: A Comparison of Interactive Reinforcement Learning Algorithms
    • Von Menschlichem, Dorothea Koert, Tag der Einreichung, Erklärung zur Master-Thesis
    • 2019
    Multi-Channel Interactive Reinforcement Learning for Sequential Tasks
    Scalable agent alignment via reward modeling: a research direction
    • 51
    • PDF
    A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems
    • 44
    • PDF
    Pitfalls of learning a reward function online
    Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop
    Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies
    • 1
    • PDF

    References

    SHOWING 1-10 OF 59 REFERENCES
    Principled Methods for Advising Reinforcement Learning Agents
    • 110
    • PDF
    Augmenting Reinforcement Learning with Human Feedback
    • 15
    • PDF
    Interactively shaping agents via human reinforcement: the TAMER framework
    • 294
    • PDF
    Policy Shaping: Integrating Human Feedback with Reinforcement Learning
    • 200
    • PDF
    Creating Advice-Taking Reinforcement Learners
    • 177
    • PDF
    Teaching on a budget: agents advising agents in reinforcement learning
    • 103
    • PDF
    Learning in Reinforcement Learning
    • 2
    • PDF
    Dynamic potential-based reward shaping
    • 95
    • PDF