paper-with-me

홈 › Papers

On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies

2022-09-21 · Haozhi Wang, Qing Wang, Yunfeng Shao, Dong Li, Jianye Hao, Yinchuan Li

Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance. However, the gradient conflict problem is still poorly understood in Meta-RL, which may lead to performance degradation when encountering distinct tasks. To tackle this challenge, this paper proposes a novel personalized Meta-RL (pMeta-RL) algorithm, which aggregates task-specific personalized policies to update a meta-policy used for all tasks, while maintaining personalized policies to maximize the average return of each task under the constraint of the meta-policy. We also provide the theoretical analysis under the tabular setting, which demonstrates the convergence of our pMeta-RL algorithm. Moreover, we extend the proposed pMeta-RL algorithm to a deep network version based on soft actor-critic, making it suitable for continuous control tasks. Experiment results show that the proposed algorithms outperform other previous Meta-RL algorithms on Gym and MuJoCo suites.

📄 PDF Abstract BibTeX arXiv:2209.10072

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlMeta-LearningMeta Reinforcement LearningMuJoCoreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Meta Generative Flow Networks with Personalization for Task-Specific Adaptation

2023-06-16 · Xinyuan Ji, Xu Zhang, Wei Xi, Haozhi Wang 외

Multi-task reinforcement learning and meta-reinforcement learning have been developed to quickly adapt to new tasks, but they tend to focus on tasks with higher rewards and more frequent occurrences, leading to poor perf…

Meta-LearningMeta Reinforcement Learningreinforcement-learningReinforcement Learning

Characterizing Policy Divergence for Personalized Meta-Reinforcement Learning

2020-10-09 · Michael Zhang

Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to perso…

DiversityMeta-LearningMeta Reinforcement Learningreinforcement-learning+2

Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offs

2024-06-17 · Haifeng Wen, Hong Xing, Osvaldo Simeone

For modern artificial intelligence (AI) applications such as large language models (LLMs), the training paradigm has recently shifted to pre-training followed by fine-tuning. Furthermore, owing to dwindling open reposito…

Federated LearningMeta-Learning

Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes

2023-01-17 · Konstantin Mishchenko, Slavomír Hanzely, Peter Richtárik

In this work, we consider the problem of minimizing the sum of Moreau envelopes of given functions, which has previously appeared in the context of meta-learning and personalized federated learning. In contrast to the ex…

Federated LearningMeta-LearningPersonalized Federated Learning

Interpretable Personalized Experimentation

2021-11-05 · Han Wu, Sarah Tan, Weiwei Li, Mia Garrard 외

Black-box heterogeneous treatment effect (HTE) models are increasingly being used to create personalized policies that assign individuals to their optimal treatments. However, they are difficult to understand, and can be…