Value Driven Representation for Human-in-the-Loop Reinforcement Learning

2020-04-02 · Ramtin Keramati, Emma Brunskill

Interactive adaptive systems powered by Reinforcement Learning (RL) have many potential applications, such as intelligent tutoring systems. In such systems there is typically an external human system designer that is creating, monitoring and modifying the interactive adaptive system, trying to improve its performance on the target outcomes. In this paper we focus on algorithmic foundation of how to help the system designer choose the set of sensors or features to define the observation space used by reinforcement learning agent. We present an algorithm, value driven representation (VDR), that can iteratively and adaptively augment the observation space of a reinforcement learning agent so that is sufficient to capture a (near) optimal policy. To do so we introduce a new method to optimistically estimate the value of a policy using offline simulated Monte Carlo rollouts. We evaluate the performance of our approach on standard RL benchmarks with simulated humans and demonstrate significant improvement over prior baselines.

📄 PDF Abstract BibTeX arXiv:2004.01223

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

MR-ARL: Model Reference Adaptive Reinforcement Learning for Robustly Stable On-Policy Data-Driven LQR

2024-02-22 · Marco Borghesi, Alessandro Bosso, Giuseppe Notarstefano

This article introduces a novel framework for data-driven linear quadratic regulator (LQR) design. First, we introduce a reinforcement learning paradigm for on-policy data-driven LQR, where exploration and exploitation a…

reinforcement-learning Reinforcement Learning

Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification

2019-10-01 · ICCV 2019 10 · Zimo Liu, Jingya Wang, Shaogang Gong, Huchuan Lu 외

Most existing person re-identification(Re-ID) approaches achieve superior results based on the assumption that a large amount of pre-labelled data is usually available and can be put into training phrase all at once. How…

Active Learning Deep Reinforcement Learning Person Re-Identification reinforcement-learning+3

Data Driven Reward Initialization for Preference based Reinforcement Learning

2023-02-17 · Mudit Verma, Subbarao Kambhampati

Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt to approximate the human's underlying re…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reinforcement Learning-based Control of Nonlinear Systems using Carleman Approximation: Structured and Unstructured Designs

2023-02-21 · Jishnudeep Kar, He Bai, Aranya Chakrabortty

We develop data-driven reinforcement learning (RL) control designs for input-affine nonlinear systems. We use Carleman linearization to express the state-space representation of the nonlinear dynamical model in the Carle…

Reinforcement Learning (RL)

Task-oriented grasping for dexterous robots using postural synergies and reinforcement learning

2026-02-24 · Dimitrios Dimou, José Santos-Victor, Plinio Moreno arxiv

In this paper, we address the problem of task-oriented grasping for humanoid robots, emphasizing the need to align with human social norms and task-specific objectives. Existing methods, employ a variety of open-loop and…

Reinforcement Learning