mlsanityData to 7 Oct 2026

Improving Generalization in Meta Reinforcement Learning using Learned Objectives

arXiv 1910.04098 ↗First posted 9 Oct 2019cs.LG cs.AI cs.NEcited by 68

Not on the map. Why?

Abstract (arXiv)

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function that decides how future individuals will learn. Unlike recent meta-RL algorithms, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training. In some cases, it even outperforms human-engineered RL algorithms. MetaGenRL uses off-policy second-order gradients during meta-training that greatly increase its sample efficiency.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 20; 2022: 18; 2023: 10; 2024: 8; 2025: 8; 2026: 3.

68 papers.

Sort:

By area:

  1. 2022Discovered Policy Optimisationcited by 103
  2. 2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 102
  3. 2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 92
  4. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  5. 2021Tactical Optimism and Pessimism for Deep Reinforcement Learningcited by 55
  6. 2021Offline Meta-Reinforcement Learning with Online Self-Supervisioncited by 52
  7. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  8. 2021Evolving Reinforcement Learning Algorithmscited by 48
  9. 2021Bootstrapped Meta-Learningcited by 45
  10. 2022Discovering Evolution Strategies via Meta-Black-Box Optimizationcited by 44
  11. 2024Discovering Preference Optimization Algorithms with and for Large Language Modelscited by 38
  12. 2021Fast and Slow Learning of Recurrent Independent Mechanismscited by 36
38 more
  1. 2025LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilitiescited by 36
  2. 2021Procedural Generalization by Planning with Self-Supervised World Modelscited by 30
  3. 2021Introducing Symmetries to Black Box Meta Reinforcement Learningcited by 25
  4. 2024Retrieval-Augmented Decision Transformer: External Memory for In-context RLcited by 20
  5. 2022On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learningcited by 18
  6. 2024Discovering Temporally-Aware Reinforcement Learning Algorithmscited by 18
  7. 2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
  8. 2023Discovering General Reinforcement Learning Algorithms with Adversarial Environment Designcited by 16
  9. 2023Behavior Alignment via Reward Function Optimizationcited by 16
  10. 2024Can Learned Optimization Make Reinforcement Learning Less Difficult?cited by 14
  11. 2021Searching for Robustness: Loss Learning for Noisy Classification Taskscited by 13
  12. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  13. 2021Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixturecited by 12
  14. 2022Reinforcement Learning with Automated Auxiliary Loss Searchcited by 12
  15. 2022Eliminating Meta Optimization Through Self-Referential Meta Learningcited by 12
  16. 2023Learning to Optimize for Reinforcement Learningcited by 12
  17. 2021A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learningcited by 11
  18. 2022Meta-Gradients in Non-Stationary Environmentscited by 11
  19. 2025Evolution and The Knightian Blindspot of Machine Learningcited by 11
  20. 2022Automated Reinforcement Learning: An Overviewcited by 9
  21. 2022A Simple Guard for Learned Optimizerscited by 9
  22. 2022Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classificationcited by 9
  23. 2022Learning Symbolic Model-Agnostic Loss Functions via Meta-Learningcited by 9
  24. 2023Deep Model Predictive Optimizationcited by 7
  25. 2021On the Practical Consistency of Meta-Reinforcement Learning Algorithmscited by 6
  26. 2023Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imaginationcited by 6
  27. 2021One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learningcited by 5
  28. 2025How Should We Meta-Learn Reinforcement Learning Algorithms?cited by 5
  29. 2021Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularizationcited by 4
  30. 2021Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learningcited by 4
  31. 2022An Investigation of the Bias-Variance Tradeoff in Meta-Gradientscited by 4
  32. 2026Training AI Scientists to Replicate Researchcited by 4
  33. 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNscited by 3
  34. 2024AutoFT: Learning an Objective for Robust Fine-Tuningcited by 3
  35. 2021Neural Auto-Curriculacited by 2
  36. 2023Optimistic Meta-Gradientscited by 2
  37. 2024Meta-Learning Objectives for Preference Optimizationcited by 2
  38. 2021Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific researchcited by 1

50 most cited of 68 All 68 (JSON)