mlsanityData to 7 Oct 2026

Dynamic Context Scheduling: Learning Beyond the Static Universe

arXiv 2608.20799 ↗First posted 21 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We study dynamic context scheduling as a training instrument for contextual re- inforcement learning. Rather than treating intra-episode context variation as a deployment reality, we treat it as a controlled shaping mechanism. Thereby, context evolves within each training episode according to a predetermined schedule, expos- ing the policy to a richer and more temporally structured region of the environment parameter space. We introduce DYNAMICCARLENV, a framework that wraps contextual environments with pluggable schedule families, such as sinusoidal off- sets or cosine annealing. Across CartPole, BipedalWalker and VehicleRacing with CARL contextualization, we show that dynamic schedules match or outperform static context baselines in the out-of-distribution (OOD) regimes. Interestingly, for the more complex BipedalWalker and VehicleRacing environments we also achieve higher in-distribution (ID) evaluation performance. Preliminary findings indicate that automatic search for multi-stage curricula can successfully discover schedules that improve generalization, performing comparably to extensive grid search over single-stage schedulers.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 52 references that are in the map. First posted on arXiv 21 Aug 2026.

Builds on

43 of 52 references.

References · 43

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  5. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  6. 2018DeepMind Control Suitecited by 935
  7. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  8. 2019Solving Rubik's Cube with a Robot Handcited by 699
  9. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  10. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  11. 2017Robust Adversarial Reinforcement Learningcited by 439
  12. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
31 more
  1. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
  2. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  3. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  4. 2015Contextual Markov Decision Processescited by 213
  5. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  6. 2018Assessing Generalization in Deep Reinforcement Learningcited by 132
  7. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 129
  8. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 113
  9. 2023A Tutorial on Meta-Reinforcement Learningcited by 102
  10. 2022Robust Reinforcement Learning using Offline Datacited by 95
  11. 2017Markov Decision Processes with Continuous Side Informationcited by 54
  12. 2020Self-Paced Deep Reinforcement Learningcited by 49
  13. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 41
  14. 2019Environment Probing Interaction Policiescited by 39
  15. 2022Transformers are Meta-Reinforcement Learnerscited by 39
  16. 2020Optimizing for the Future in Non-Stationary MDPscited by 37
  17. 2023AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agentscited by 36
  18. 2021Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentscited by 35
  19. 2022Context is Everything: Implicit Identification for Dynamics Adaptationcited by 26
  20. 2023Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policiescited by 18
  21. 2024Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalizationcited by 16
  22. 2022Latent Variable Representation for Reinforcement Learningcited by 14
  23. 2023Reinforcement Learning with History-Dependent Dynamic Contextscited by 11
  24. 2023Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RLcited by 10
  25. 2022Hyperparameters in Contextual RL are Highly Situationalcited by 4
  26. 2025Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policiescited by 4
  27. 2025Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policycited by 4
  28. 2025Shared Modular Recurrence in Contextual MDPs for Universal Morphology Controlcited by 3
  29. 2024Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learningcited by 2
  30. 2026Structure Detection for Contextual Reinforcement Learningcited by 2
  31. 2026Contextual Intelligence The Next Leap for Reinforcement Learningcited by 1

Built on by

Not cited yet.