DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction

2022-03-01 · Masashi Okada, Tadahiro Taniguchi

The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pixels that uses discrete world models to represent latent states with categorical variables. Dreaming is also a form of reinforcement learning from pixels that attempts to avoid the autoencoding process in general world model training by involving a reconstruction-free contrastive learning objective. The proposed DreamingV2 is a novel approach of adopting both the discrete representation of DreamingV2 and the reconstruction-free objective of Dreaming. Compared to DreamerV2 and other recent model-based methods without reconstruction, DreamingV2 achieves the best scores on five simulated challenging 3D robot arm tasks. We believe that DreamingV2 will be a reliable solution for robot learning since its discrete representation is suitable to describe discontinuous environments, and the reconstruction-free fashion well manages complex vision observations.

📄 PDF Abstract BibTeX arXiv:2203.00494

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningModel-based Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Multi-View Dreaming: Multi-View World Model with Contrastive Learning

2022-03-15 · Akira Kinose, Masashi Okada, Ryo Okumura, Tadahiro Taniguchi

In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most current reinforcement learning method as…

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

DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces

2023-06-28 · Pranavi Pathakota, Hardik Meisheri, Harshad Khadilkar

The ability to learn robust policies while generalizing over large discrete action spaces is an open challenge for intelligent systems, especially in noisy environments that face the curse of dimensionality. In this pape…

Decoder Product Recommendation

Discrete World Models via Regularization

2026-03-02 · Davide Bizzaro, Luciano Serafini arxiv

World models aim to capture the states and dynamics of an environment in a compact latent space. Moreover, using Boolean state representations is particularly useful for search heuristics and symbolic reasoning and plann…

Learning Discrete World Models for Heuristic Search

2024-09-14 · Reinforcement Learning Journal 2024 9 · Forest Agostinelli, Misagh Soltani

For many sequential decision making problems, planning is often necessary to find solutions. However, for domains such as those encountered in robotics, the transition function, also known as the world model, is often un…

Deep Reinforcement Learning Heuristic Search Model-based Reinforcement Learning Reinforcement Learning+4

Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling

2018-07-01 · ICML 2018 7 · Kyowoon Lee, Sol-A Kim, Jaesik Choi, Seong-Whan Lee

Many real-world applications of reinforcement learning require an agent to select optimal actions from continuous spaces. Recently, deep neural networks have successfully been applied to games with discrete actions …

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