mlsanityData to 14 Oct 2026

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

arXiv 1710.03641 ↗First posted 10 Oct 2017cs.LG cs.AIcited by 108

Not on the map. Why?

Cited by 21 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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 adaptation into the learning-to-learn framework. We develop a simple gradient-based meta-learning algorithm suitable for adaptation in dynamically changing and adversarial scenarios. Additionally, we design a new multi-agent competitive environment, RoboSumo, and define iterated adaptation games for testing various aspects of continuous adaptation strategies. We demonstrate that meta-learning enables significantly more efficient adaptation than reactive baselines in the few-shot regime. Our experiments with a population of agents that learn and compete suggest that meta-learners are the fittest.

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 28; 2022: 19; 2023: 22; 2024: 12; 2025: 11; 2026: 15.

108 papers.

Sort:

By area:

  1. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
  2. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 133
  3. 2022MetaMorph: Learning Universal Controllers with Transformerscited by 89
  4. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  5. 2021Continual Backprop: Stochastic Gradient Descent with Persistent Randomnesscited by 80
  6. 2023RMM: Reinforced Memory Management for Class-Incremental Learningcited by 66
  7. 2022Model-Free Opponent Shapingcited by 44
  8. 2021How Fine-Tuning Allows for Effective Meta-Learningcited by 41
  9. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Modelscited by 38
  10. 2022Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learningcited by 35
  11. 2021Continuous Coordination As a Realistic Scenario for Lifelong Learningcited by 32
  12. 2022Factored Adaptation for Non-Stationary Reinforcement Learningcited by 30
38 more
  1. 2021Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platformscited by 22
  2. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  3. 2021Model-Based Opponent Modelingcited by 22
  4. 2022Proximal Learning With Opponent-Learning Awarenesscited by 20
  5. 2022Influencing Long-Term Behavior in Multiagent Reinforcement Learningcited by 18
  6. 2021ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxationcited by 17
  7. 2021On Data Efficiency of Meta-learningcited by 16
  8. 2023Curious Replay for Model-based Adaptationcited by 16
  9. 2021CoMPS: Continual Meta Policy Searchcited by 15
  10. 2022An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Contextcited by 15
  11. 2021Continual Learning In Environments With Polynomial Mixing Timescited by 14
  12. 2021A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learningcited by 12
  13. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  14. 2023Scaling Opponent Shaping to High Dimensional Gamescited by 12
  15. 2023Online Continual Learning on Hierarchical Label Expansioncited by 11
  16. 2023LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platformscited by 11
  17. 2021Meta-Reinforcement Learning in Broad and Non-Parametric Environmentscited by 10
  18. 2022Reinforcement Learning in Presence of Discrete Markovian Context Evolutioncited by 9
  19. 2021Meta-Reinforcement Learning by Tracking Task Non-stationaritycited by 8
  20. 2024LOQA: Learning with Opponent Q-Learning Awarenesscited by 8
  21. 2022On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptationcited by 7
  22. 2023Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RLcited by 7
  23. 2024Fast Peer Adaptation with Context-aware Explorationcited by 7
  24. 2024Advantage Alignment Algorithmscited by 7
  25. 2021A Channel Coding Benchmark for Meta-Learningcited by 6
  26. 2023Online Reinforcement Learning in Non-Stationary Context-Driven Environmentscited by 6
  27. 2023Learning Diverse Risk Preferences in Population-based Self-playcited by 6
  28. 2023Meta-Value Learning: a General Framework for Learning with Learning Awarenesscited by 6
  29. 2025CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language Modelscited by 6
  30. 2021Dealing with Non-Stationarity in MARL via Trust-Region Decompositioncited by 5
  31. 2021Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluationcited by 5
  32. 2021Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularizationcited by 5
  33. 2021Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learningcited by 5
  34. 2022An Investigation of the Bias-Variance Tradeoff in Meta-Gradientscited by 5
  35. 2022A Reinforcement Learning Approach to Estimating Long-term Treatment Effectscited by 5
  36. 2023Convergence of Gradient-based MAML in LQRcited by 5
  37. 2021Dynamic Regret Analysis for Online Meta-Learningcited by 4
  38. 2021Reinforcement Learning In Two Player Zero Sum Simultaneous Action Gamescited by 4

50 most cited of 108 All 108 (JSON)