Disentangled Predictive Representation for Meta-Reinforcement Learning

2021-06-13 · ICML Workshop URL 2021 7 · Sephora Madjiheurem, Laura Toni

A major challenge in reinforcement learning is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcement learning, which identifies common structures among past tasks to be then generalized to new tasks (meta-test). Prior works learn meta-representation jointly while solving tasks, resulting in representations that not generalize well across policies, leading to sampling-inefficiency during meta-test phases. In this work, we introduce state2vec, an efficient and low-complexity unsupervised framework for learning disentangled representations that are more general. The state embedding vectors learned with state2vec capture the geometry of the underlying state space, resulting in high-quality basis functions for linear value function approximation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Meta Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

2022-10-01 · Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang 외

Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from relate…

Disentanglement Meta Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability

2025-10-24 · Po-Chen Kuo, Han Hou, Will Dabney, Edgar Y. Walker arxiv

Learning a compact representation of history is critical for planning and generalization in partially observable environments. While meta-reinforcement learning (RL) agents can attain near Bayes-optimal policies, they of…

Representation Learning Reinforcement Learning Bayesian Inference

DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks

2025-03-12 · Wei Cui, Tongzi Wu, Jesse C. Cresswell, Yi Sui 외

Meta-learning represents a strong class of approaches for solving few-shot learning tasks. Nonetheless, recent research suggests that simply pre-training a generic encoder can potentially surpass meta-learning algorithms…

Diversity Few-Shot Learning Meta-Learning Representation Learning

DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis

2024-10-23 · Shangshang Yang, Mingyang Chen, Ziwen Wang, Xiaoshan Yu 외

Existing graph learning-based cognitive diagnosis (CD) methods have made relatively good results, but their student, exercise, and concept representations are learned and exchanged in an implicit unified graph, which mak…

cognitive diagnosis Diagnostic Graph Attention Graph Learning

Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning

2025-09-01 · Seonsoo Kim, Jun-Gill Kang, Taehong Kim, Seongil Hong arxiv

In meta-learning and its downstream tasks, many methods rely on implicit adaptation to task variations, where multiple factors are mixed together in a single entangled representation. This makes it difficult to interpret…

Reinforcement Learning