Deep Reinforcement Learning from Policy-Dependent Human Feedback

2019-02-12 · Dilip Arumugam, Jun Ki Lee, Sophie Saskin, Michael L. Littman

To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of time while efficiently leveraging the sparse feedback a human trainer is capable of providing. Recent work has shown that human feedback can be characterized as a critique of an agent's current behavior rather than as an alternative reward signal to be maximized, culminating in the COnvergent Actor-Critic by Humans (COACH) algorithm for making direct policy updates based on human feedback. Our work builds on COACH, moving to a setting where the agent's policy is represented by a deep neural network. We employ a series of modifications on top of the original COACH algorithm that are critical for successfully learning behaviors from high-dimensional observations, while also satisfying the constraint of obtaining reduced sample complexity. We demonstrate the effectiveness of our Deep COACH algorithm in the rich 3D world of Minecraft with an agent that learns to complete tasks by mapping from raw pixels to actions using only real-time human feedback in 10-15 minutes of interaction.

📄 PDF Abstract BibTeX arXiv:1902.04257

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningMinecraftreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Interactive Learning from Policy-Dependent Human Feedback

2017-01-21 · ICML 2017 8 · James MacGlashan, Mark K. Ho, Robert Loftin, Bei Peng 외

This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has made the assumption that people provide…

Policy Shaping: Integrating Human Feedback with Reinforcement Learning

2013-12-01 · NeurIPS 2013 12 · Shane Griffith, Kaushik Subramanian, Jonathan Scholz, Charles L. Isbell 외

A long term goal of Interactive Reinforcement Learning is to incorporate non-expert human feedback to solve complex tasks. State-of-the-art methods have approached this problem by mapping human information to reward and …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Influencing Reinforcement Learning through Natural Language Guidance

2021-04-04 · Tasmia Tasrin, Md Sultan Al Nahian, Habarakadage Perera, Brent Harrison

Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that is either positive or negative. Whi…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Data-dependent Exploration for Online Reinforcement Learning from Human Feedback

2026-05-06 · Zhen-Yu Zhang, Yuting Tang, Jiandong Zhang, Lanjihong Ma 외 arxiv

Online reinforcement learning from human feedback (RLHF) has emerged as a promising paradigm for aligning large language models (LLMs) by continuously collecting new preference feedback during training. A foundational ch…

Reinforcement Learning

Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback

2021-09-15 · Ishaan Shah, David Halpern, Kavosh Asadi, Michael L. Littman

Fluid human-agent communication is essential for the future of human-in-the-loop reinforcement learning. An agent must respond appropriately to feedback from its human trainer even before they have significant experience…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)