paper-with-me

홈 › Papers

Meta-Gradients in Non-Stationary Environments

2022-09-13 · Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel, Tom Zahavy, Satinder Singh

Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement learning problems. However, the properties of meta-gradients in such environments have not been systematically studied. In this work, we bring new clarity to meta-gradients in non-stationary environments. Concretely, we ask: (i) how much information should be given to the learned optimizers, so as to enable faster adaptation and generalization over a lifetime, (ii) what meta-optimizer functions are learned in this process, and (iii) whether meta-gradient methods provide a bigger advantage in highly non-stationary environments. To study the effect of information provided to the meta-optimizer, as in recent works (Flennerhag et al., 2021; Almeida et al., 2021), we replace the tuned meta-parameters of fixed update rules with learned meta-parameter functions of selected context features. The context features carry information about agent performance and changes in the environment and hence can inform learned meta-parameter schedules. We find that adding more contextual information is generally beneficial, leading to faster adaptation of meta-parameter values and increased performance over a lifetime. We support these results with a qualitative analysis of resulting meta-parameter schedules and learned functions of context features. Lastly, we find that without context, meta-gradients do not provide a consistent advantage over the baseline in highly non-stationary environments. Our findings suggest that contextualizing meta-gradients can play a pivotal role in extracting high performance from meta-gradients in non-stationary settings.

📄 PDF Abstract BibTeX arXiv:2209.06159

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference

2018-10-29 · ICLR 2019 5 · Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu 외

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a n…

Continual LearningMeta-LearningReinforcement Learning

On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning

2020-02-12 · NeurIPS 2021 12 · Alireza Fallah, Kristian Georgiev, Aryan Mokhtari, Asuman Ozdaglar

We consider Model-Agnostic Meta-Learning (MAML) methods for Reinforcement Learning (RL) problems, where the goal is to find a policy using data from several tasks represented by Markov Decision Processes (MDPs) that can …

Meta-LearningMeta Reinforcement LearningPolicy Gradient Methodsreinforcement-learning+2

Double Meta-Learning for Data Efficient Policy Optimization in Non-Stationary Environments

2020-11-21 · Elahe Aghapour, Nora Ayanian

We are interested in learning models of non-stationary environments, which can be framed as a multi-task learning problem. Model-free reinforcement learning algorithms can achieve good asymptotic performance in multi-tas…

Meta-LearningMeta Reinforcement LearningMulti-Task Learningreinforcement-learning+2

Non-stationary Online Convex Optimization with Arbitrary Delays

2023-05-20 · Yuanyu Wan, Chang Yao, Mingli Song, Lijun Zhang

Online convex optimization (OCO) with arbitrary delays, in which gradients or other information of functions could be arbitrarily delayed, has received increasing attention recently. Different from previous studies that …

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

2017-10-10 · ICLR 2018 1 · Maruan Al-Shedivat, Trapit Bansal, Yuri Burda, Ilya Sutskever 외

Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence. In this paper, we cast the problem of continuous adaptatio…

Meta-Learning