mlsanityData to 7 Oct 2026

Learning to Learn: Meta-Critic Networks for Sample Efficient Learning

arXiv 1706.09529 ↗First posted 29 Jun 2017cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning. The key idea is to learn a meta-critic: an action-value function neural network that learns to criticise any actor trying to solve any specified task. For supervised learning, this corresponds to the novel idea of a trainable task-parametrised loss generator. This meta-critic approach provides a route to knowledge transfer that can flexibly deal with few-shot and semi-supervised conditions for both reinforcement and supervised learning. Promising results are shown on both reinforcement and supervised learning problems.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 9; 2022: 6; 2023: 6; 2024: 2; 2025: 3; 2026: 1.

28 papers.

Sort:

By area:

  1. 2021Meta-learning PINN loss functionscited by 51
  2. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  3. 2021Recomposing the Reinforcement Learning Building Blocks with Hypernetworkscited by 33
  4. 2019Watch, Try, Learn: Meta-Learning from Demonstrations and Rewardcited by 26
  5. 2022On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learningcited by 18
  6. 2021CoMPS: Continual Meta Policy Searchcited by 15
  7. 2021Learning an Explicit Hyperparameter Prediction Function Conditioned on Taskscited by 9
  8. 2022Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approachcited by 9
  9. 2023Efficient Symbolic Policy Learning with Differentiable Symbolic Expressioncited by 9
  10. 2021Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RLcited by 8
  11. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  12. 2022Simple Emergent Action Representations from Multi-Task Policy Trainingcited by 6
16 more
  1. 2022Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Taskscited by 5
  2. 2025Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solvingcited by 4
  3. 2021Adapting to Dynamic LEO-B5G Systems: Meta-Critic Learning Based Efficient Resource Schedulingcited by 3
  4. 2021Meta-Reinforcement Learning for Heuristic Planningcited by 2
  5. 2021Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learningcited by 1
  6. 2023Human-Inspired Framework to Accelerate Reinforcement Learningcited by 1
  7. 2024Black Box Meta-Learning Intrinsic Rewardscited by 1
  8. 2024Relation-Aware Meta-Learning for Zero-shot Sketch-Based Image Retrievalcited by 1
  9. 2025Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Reviewcited by 1
  10. 2022Model Based Meta Learning of Critics for Policy Gradientscited by 0
  11. 2022Implicit Training of Energy Model for Structure Predictioncited by 0
  12. 2023Acceleration in Policy Optimizationcited by 0
  13. 2023RL3: Boosting Meta Reinforcement Learning via RL inside RL2cited by 0
  14. 2023Hypothesis Network Planned Exploration for Rapid Meta-Reinforcement Learning Adaptationcited by 0
  15. 2025Adaptive Policy Backbone via Shared Networkcited by 0
  16. 2026Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systemscited by 0