paper-with-me

홈 › Papers

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity

2024-11-02 · Emiliyan Gospodinov, Vaisakh Shaj, Philipp Becker, Stefan Geyer, Gerhard Neumann

Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In this work, we introduce a new formalism, Hidden Parameter-POMDP, designed for control with adaptive world models. We demonstrate that this approach enables learning robust behaviors across a variety of non-stationary RL benchmarks. Additionally, this formalism effectively learns task abstractions in an unsupervised manner, resulting in structured, task-aware latent spaces.

📄 PDF Abstract BibTeX arXiv:2411.01342

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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 Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)

RISE: Adaptive Imagination for World Action Models

2026-08-20 · Hongbo Lu, Liang Yao, Chenghao He, Hao Han 외 hf

World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagination budget to every scene. We propose RISE (Refining Imagination t…

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

2021-03-08 · Axel Brunnbauer, Luigi Berducci, Andreas Brandstätter, Mathias Lechner 외

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel input…

Autonomous Racingcontinuous-controlContinuous ControlDeep Reinforcement Learning+1

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)

Choreographer: Learning and Adapting Skills in Imagination

2022-11-23 · Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Alexandre Lacoste 외

Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment. However, without appropriate k…

Unsupervised Reinforcement Learning