paper-with-me

홈 › Papers

Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder

2019-03-22 · Heecheol Kim, Masanori Yamada, Kosuke Miyoshi, Hiroshi Yamakawa

One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimensionality of the action space with regard to the time axis. However, previous studies relied on humans defining macro actions or assumed macro actions as repetitions of the same primitive actions. We present Factorized Macro Action Reinforcement Learning (FaMARL) which autonomously learns disentangled factor representation of a sequence of actions to generate macro actions that can be directly applied to general reinforcement learning algorithms. FaMARL exhibits higher scores than other reinforcement learning algorithms on environments that require an extensive amount of search.

📄 PDF Abstract BibTeX arXiv:1903.09366

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementGeneral Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Disentangling Action Sequences: Discovering Correlated Samples

2020-10-17 · Jiantao Wu, Lin Wang

Disentanglement is a highly desirable property of representation due to its similarity with human's understanding and reasoning. This improves interpretability, enables the performance of down-stream tasks, and enables c…

Disentanglement

Reusability and Transferability of Macro Actions for Reinforcement Learning

2019-08-05 · Yi-Hsiang Chang, Kuan-Yu Chang, Henry Kuo, Chun-Yi Lee

Conventional reinforcement learning (RL) typically determines an appropriate primitive action at each timestep. However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to byp…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders

2017-11-24 · Momchil Peychev, Petar Veličković, Pietro Liò

The notion of disentangled autoencoders was proposed as an extension to the variational autoencoder by introducing a disentanglement parameter $\beta$, controlling the learning pressure put on the possible underlying lat…

Disentanglement

CausalDisenSeg: A Causality-Guided Disentanglement Framework with Counterfactual Reasoning for Robust Brain Tumor Segmentation Under Missing Modalities

2026-04-15 · Bo Liu, Yulong Zou, Jin Hong arxiv

In clinical practice, the robustness of deep learning models for multimodal brain tumor segmentation is severely compromised by incomplete MRI data. This vulnerability stems primarily from modality bias, where models exp…

Brain Tumor Segmentation

Learning Disentangled Representations for Recommendation

2019-10-31 · NeurIPS 2019 12 · Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang 외

User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users' decision making processes. The factors are highly entangled, and may range from high-level ones th…

Decision MakingDisentanglementRecommendation Systems