Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement
learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly …
learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly …
[PDF][PDF] Efficient offline meta-reinforcement learning via robust task representations and adaptive policy generation
Z Li, Z Lin, Y Chen, Z Liu - Proceedings of the Thirty-Third International …, 2024 - ijcai.org
Zero-shot adaptation is crucial for agents facing new tasks. Offline Meta-Reinforcement
Learning (OMRL), utilizing offline multi-task datasets to train policies, offers a way to attain …
Learning (OMRL), utilizing offline multi-task datasets to train policies, offers a way to attain …
SCORE: Simple Contrastive Representation and Reset-Ensemble for offline meta-reinforcement learning
H Yang, K Lin, T Yang, G Sun - Knowledge-Based Systems, 2025 - Elsevier
Offline meta-reinforcement learning (OMRL) aims to train agents to quickly adapt to new
tasks using only pre-collected data. However, existing OMRL methods often involve …
tasks using only pre-collected data. However, existing OMRL methods often involve …
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
A longstanding goal of artificial general intelligence is highly capable generalists that can
learn from diverse experiences and generalize to unseen tasks. The language and vision …
learn from diverse experiences and generalize to unseen tasks. The language and vision …
Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding
S He, C Yu, Q Lin, S Mao, B Tang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Real-time bidding (RTB) plays a pivotal role in online advertising ecosystems. Advertisers
employ strategic bidding to optimize their advertising impact while adhering to various …
employ strategic bidding to optimize their advertising impact while adhering to various …
Scrutinize What We Ignore: Reining Task Representation Shift In Context-Based Offline Meta Reinforcement Learning
Offline meta reinforcement learning (OMRL) has emerged as a promising approach for
interaction avoidance and strong generalization performance by leveraging pre-collected …
interaction avoidance and strong generalization performance by leveraging pre-collected …
Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning
A Scannell, J Pajarinen - arXiv preprint arXiv:2412.14834, 2024 - arxiv.org
Offline meta-reinforcement learning aims to equip agents with the ability to rapidly adapt to
new tasks by training on data from a set of different tasks. Context-based approaches utilize …
new tasks by training on data from a set of different tasks. Context-based approaches utilize …
Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
Developing policies that can adjust to non-stationary environments is essential for real-world
reinforcement learning applications. However, learning such adaptable policies in offline …
reinforcement learning applications. However, learning such adaptable policies in offline …
Disentangled Task Representation Learning for Offline Meta Reinforcement Learning
S Cong, C Yu, Y Wang, D Jiang… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
In this paper, we aim to address the generalization problem in Offline Meta-Reinforcement
Learning (OMRL) when both task objectives and environmental parameters vary …
Learning (OMRL) when both task objectives and environmental parameters vary …
Zero-Shot Task-Level Adaptation via Coarse-to-Fine Policy Refinement and Holistic-Local Contrastive Representations
Z Li, Z Lin, C Yurou, L Zhang, Z Liu - openreview.net
Meta-reinforcement learning offers a mechanism for zero-shot adaptation, enabling agents
to handle new tasks with parametric variation in real-world environments. However, existing …
to handle new tasks with parametric variation in real-world environments. However, existing …