Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
arXiv:2103.08233 · doi:10.1109/ICASSP39728.2021.9413446
Abstract
Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks. The model initialized by provided weight can be fine-tuned to an unseen task despite only using a small amount of samples and within a few adaptation steps. MAML is simple and versatile but requires costly learning rate tuning and careful design of the task distribution which affects its scalability and generalization. This paper proposes a more robust MAML based on an adaptive learning scheme and a prioritization task buffer(PTB) referred to as Robust MAML (RMAML) for improving scalability of training process and alleviating the problem of distribution mismatch. RMAML uses gradient-based hyper-parameter optimization to automatically find the optimal learning rate and uses the PTB to gradually adjust train-ing task distribution toward testing task distribution over the course of training. Experimental results on meta reinforcement learning environments demonstrate a substantial performance gain as well as being less sensitive to hyper-parameter choice and robust to distribution mismatch.
References in corpus (11)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Practical Bayesian Optimization of Machine Learning Algorithms
- Prototypical Networks for Few-shot Learning
- Trust Region Policy Optimization
- On First-Order Meta-Learning Algorithms
- RL: Fast Reinforcement Learning via Slow Reinforcement Learning
- Gradient-based Hyperparameter Optimization through Reversible Learning
- Distributed Distributional Deterministic Policy Gradients
- How to train your MAML
- Online Learning Rate Adaptation with Hypergradient Descent
- Curriculum in Gradient-Based Meta-Reinforcement Learning