Explaining Conditions for Reinforcement Learning Behaviors from Real and Imagined Data

2020-11-17 · Aastha Acharya, Rebecca Russell, Nisar R. Ahmed

The deployment of reinforcement learning (RL) in the real world comes with challenges in calibrating user trust and expectations. As a step toward developing RL systems that are able to communicate their competencies, we present a method of generating human-interpretable abstract behavior models that identify the experiential conditions leading to different task execution strategies and outcomes. Our approach consists of extracting experiential features from state representations, abstracting strategy descriptors from trajectories, and training an interpretable decision tree that identifies the conditions most predictive of different RL behaviors. We demonstrate our method on trajectory data generated from interactions with the environment and on imagined trajectory data that comes from a trained probabilistic world model in a model-based RL setting.

📄 PDF Abstract BibTeX arXiv:2011.09004

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning (RL)

Dream to Control: Learning Behaviors by Latent Imagination

2019-12-03 · ICLR 2020 1 · Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi

Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many p…

Continuous Control reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments

2023-11-17 · Sang-Hyun Lee, Yoonjae Jung, Seung-Woo Seo

Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) by explicitly taking advantage of hierarchical structure. Modern HRL typically designs a hierarchical agent com…

Autonomous Driving Hierarchical Reinforcement Learning Reinforcement Learning (RL)

Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space

2021-02-19 · Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Lucas Liebenwein 외

Learning competitive behaviors in multi-agent settings such as racing requires long-term reasoning about potential adversarial interactions. This paper presents Deep Latent Competition (DLC), a novel reinforcement learni…

Reinforcement Learning (RL)

Increasing Data Efficiency of Driving Agent By World Model

2020-12-14 · CUHK Course IERG5350 2020 12 · Yicheng Liu, CAO Qianqian

Reinforcement learning algorithms for real-world autonomous driving must be able to handle complex, unknown dynamical systems. This requirement is han- dled well by model-free algorithm such as PPO. However, model-free a…

Autonomous Driving reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Communication in Multi-Agent Reinforcement Learning: Intention Sharing

2021-01-01 · ICLR 2021 1 · Woojun Kim, Jongeui Park, Youngchul Sung

Communication is one of the core components for learning coordinated behavior in multi-agent systems. In this paper, we propose a new communication scheme named Intention Sharing (IS) for multi-agent reinforcement learn…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)