# Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization

arXiv: https://arxiv.org/abs/2601.07164 · HTML: https://mlsanity.com/paper/2601.07164/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Placed in

- Offline RL and imitation learning from data / [Decision transformers and sequence modeling](https://mlsanity.com/offlinerl/decision-transformers-and-sequence-modeling/)

## Builds on (most cited first, 12 of 12)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [Distributional Reinforcement Learning with Quantile Regression](https://mlsanity.com/paper/1710.10044/) (2017)
- [Offline Meta-Reinforcement Learning with Advantage Weighting](https://mlsanity.com/paper/2008.06043/) (2020)
- [MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL](https://mlsanity.com/paper/2305.19923/) (2023)
- [Tactical Optimism and Pessimism for Deep Reinforcement Learning](https://mlsanity.com/paper/2102.03765/) (2021)
- [Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement](https://mlsanity.com/paper/2410.11448/) (2024)
- [Offline Meta Reinforcement Learning with In-Distribution Online Adaptation](https://mlsanity.com/paper/2305.19529/) (2023)
- [Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations](https://mlsanity.com/paper/2312.15909/) (2023)
- [Meta Reinforcement Learning with Successor Feature Based Context](https://mlsanity.com/paper/2207.14723/) (2022)

## Built on by (most cited first, 1 of 1)

- [Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning](https://mlsanity.com/paper/2610.15428/) (2026)

## Abstract (arXiv)

Offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL, promising safe and efficient knowledge acquisition by RL agents. However, OMRL still suffers extrapolation errors due to out-of-distribution (OOD) actions, compromised by broad task distributions and Markov Decision Process (MDP) ambiguity in meta-RL setups. Existing research indicates that the generalization of the Q network affects the extrapolation error in offline RL. This paper investigates this relationship by decomposing the Q value into feature and weight components, observing that while decomposition enhances adaptability and convergence in the case of high-quality data, it often leads to policy degeneration or collapse in complex tasks. We observe that decomposed Q values introduce a large estimation bias when the feature encounters OOD samples, a phenomenon we term ''feature overgeneralization''. To address this issue, we propose FLORA, which identifies OOD samples by modeling feature distributions and estimating their uncertainties. FLORA integrates a return feedback mechanism to adaptively adjust feature components. Furthermore, to learn precise task representations, FLORA explicitly models the complex task distribution using a chain of invertible transformations. We theoretically and empirically demonstrate that FLORA achieves rapid adaptation and meta-policy improvement compared to baselines across various environments.