mlsanityData to 7 Oct 2026

Meta-World Conditional Neural Processes

arXiv 2302.10320 ↗First posted 20 Feb 2023cs.LG cs.AI cs.NEcited by 1

On the map: World models → World models for language agents

Abstract (arXiv)

We propose Meta-World Conditional Neural Processes (MW-CNP), a conditional world model generator that leverages sample efficiency and scalability of Conditional Neural Processes to enable an agent to sample from its own "hallucination". We intend to reduce the agent's interaction with the target environment at test time as much as possible. To reduce the number of samples required at test time, we first obtain a latent representation of the transition dynamics from a single rollout from the test environment with hidden parameters. Then, we obtain rollouts for few-shot learning by interacting with the "hallucination" generated by the meta-world model. Using the world model representation from MW-CNP, the meta-RL agent can adapt to an unseen target environment with significantly fewer samples collected from the target environment compared to the baselines. We emphasize that the agent does not have access to the task parameters throughout training and testing, and MW-CNP is trained on offline interaction data logged during meta-training.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 17 of its 25 references that are in the map. First posted on arXiv 20 Feb 2023.

Builds on

17 of 25 references.

References · 17

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  3. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  4. 2018Conditional Neural Processescited by 421
  5. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  6. 2017One-Shot Imitation Learningcited by 232
  7. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 228
  8. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 210
  9. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 182
  10. 2019Online Meta-Learningcited by 137
  11. 2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 92
  12. 2018Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RLcited by 80
5 more
  1. 2021CoMPS: Continual Meta Policy Searchcited by 15
  2. 2021Imitation and Mirror Systems in Robots through Deep Modality Blending Networkscited by 11
  3. 2021A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learningcited by 11
  4. 2019NoRML: No-Reward Meta Learningcited by 7
  5. 2021Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spacescited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Conditional Neural Expert Processes for Learning Movement Primitives from Demonstrationcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2026Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
  2. 2026Hallucination in World Models is Predictable and Preventable
  3. 2024Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
  4. 2025HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
  5. 2018Learning Shared Dynamics with Meta-World Models
  6. 2026AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents
  7. 2025InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration
  8. 2026Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry