mlsanityData to 14 Oct 2026

RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments

arXiv 2206.12493 ↗First posted 24 Jun 2022cs.AI cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We propose RAPid-Learn: Learning to Recover and Plan Again, a hybrid planning and learning method, to tackle the problem of adapting to sudden and unexpected changes in an agent's environment (i.e., novelties). RAPid-Learn is designed to formulate and solve modifications to a task's Markov Decision Process (MDPs) on-the-fly and is capable of exploiting domain knowledge to learn any new dynamics caused by the environmental changes. It is capable of exploiting the domain knowledge to learn action executors which can be further used to resolve execution impasses, leading to a successful plan execution. This novelty information is reflected in its updated domain model. We demonstrate its efficacy by introducing a wide variety of novelties in a gridworld environment inspired by Minecraft, and compare our algorithm with transfer learning baselines from the literature. Our method is (1) effective even in the presence of multiple novelties, (2) more sample efficient than transfer learning RL baselines, and (3) robust to incomplete model information, as opposed to pure symbolic planning approaches.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 15 of its 44 references that are in the map. First posted on arXiv 24 Jun 2022.

Builds on

15 of 44 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  3. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  4. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
  5. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 78
  6. 2020Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimismcited by 76
  7. 2021Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systemscited by 24
  8. 2020Lipschitz Lifelong Reinforcement Learningcited by 23
  9. 2020SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learningcited by 23
  10. 2019Reinforcement Learning in Non-Stationary Environmentscited by 10
  11. 2019Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policycited by 10
  12. 2019Tool Macgyvering: Tool Construction Using Geometric Reasoningcited by 7
3 more
  1. 2022L2Explorer: A Lifelong Reinforcement Learning Assessment Environmentcited by 6
  2. 2019From semantics to execution: Integrating action planning with reinforcement learning for robotic causal problem-solvingcited by 5
  3. 2017Learning to Navigate Cloth using Hapticscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 3; 2026: 3.

13 papers.

Sort:

By area:

  1. 2024NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worldscited by 4
  2. 2025Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptationcited by 3
  3. 2025SLAP: Shortcut Learning for Abstract Planningcited by 3
  4. 2024Graph Pruning for Enumeration of Minimal Unsatisfiable Subsetscited by 2
  5. 2025Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Actingcited by 2
  6. 2023Heterogeneous Knowledge for Augmented Modular Reinforcement Learningcited by 1
  7. 2023Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discoverycited by 1
  8. 2024Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settingscited by 1
  9. 2024Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learningcited by 1
  10. 2026Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learningcited by 1
  11. 2023Rapid Open-World Adaptation by Adaptation Principles Learningcited by 0
  12. 2026Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Roboticscited by 0
1 more
  1. 2026Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulationcited by 0