Metadiffuser: Diffusion model as conditional planner for offline meta-rl
Recently, diffusion model shines as a promising backbone for the sequence modeling
paradigm in offline reinforcement learning (RL). However, these works mostly lack the …
paradigm in offline reinforcement learning (RL). However, these works mostly lack the …
Ode-based recurrent model-free reinforcement learning for pomdps
Neural ordinary differential equations (ODEs) are widely recognized as the standard for
modeling physical mechanisms, which help to perform approximate inference in unknown …
modeling physical mechanisms, which help to perform approximate inference in unknown …
DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planning
Dual-arm robots offer enhanced versatility and efficiency over single-arm counterparts by
enabling concurrent manipulation of multiple objects or cooperative execution of tasks using …
enabling concurrent manipulation of multiple objects or cooperative execution of tasks using …
MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components
Meta-Reinforcement Learning (Meta-RL) aims to reveal shared characteristics in dynamics
and reward functions across diverse training tasks. This objective is achieved by meta …
and reward functions across diverse training tasks. This objective is achieved by meta …
Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning
Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with
varying environmental features that require different optimal skills (ie, different modes of …
varying environmental features that require different optimal skills (ie, different modes of …
CausalCOMRL: Context-Based Offline Meta-Reinforcement Learning with Causal Representation
Z Zhang, W Meng, H Sun, G Pan - arxiv preprint arxiv:2502.00983, 2025 - arxiv.org
Context-based offline meta-reinforcement learning (OMRL) methods have achieved
appealing success by leveraging pre-collected offline datasets to develop task …
appealing success by leveraging pre-collected offline datasets to develop task …
Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with
varying environmental features that require different optimal skills (ie, different modes of …
varying environmental features that require different optimal skills (ie, different modes of …
IMLRLS: a method for ship collision avoidance by integrating meta-learning with reinforcement learning
X Jia, S Gao, W He - Third International Conference on …, 2024 - spiedigitallibrary.org
Autonomous collision avoidance is vital for intelligent ship navigation. To improve the
adaptability and effectiveness of collision avoidance policies, we propose a method that …
adaptability and effectiveness of collision avoidance policies, we propose a method that …
Dynamics Generalisation in Reinforcement Learning Through the Use of Adaptive Policies
M Beukman - 2023 - search.proquest.com
Reinforcement learning (RL) is a widely-used method for training agents to interact with an
external environment, and is commonly used in fields such as robotics. While RL has …
external environment, and is commonly used in fields such as robotics. While RL has …
[CITATION][C] A Survey of Meta-Reinforcement Learning Research
陈奕宇， 霍静， 丁天雨， 高阳 - Journal of Software, 2023