mlsanityData to 14 Oct 2026

Meta-RL with Bayesian Linear Task Models

arXiv 2512.20974 ↗First posted 24 Dec 2025cs.LG cs.AI cs.ROcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

also in 1 more
Abstract (arXiv)

Deep Bayesian reinforcement learning adapts to unseen tasks by inferring latent transition and reward models, but existing methods typically rely on variational posteriors and evidence lower bounds, introducing approximation error and unstable task representations. We introduce GLiBRL, a deep Bayesian RL framework that combines generalised linear task models with learnable non-linear basis functions. GLiBRL features conjugate Bayesian inference, yielding exact, sequential posterior updates over task parameters and model noise, together with a closed-form marginal likelihood that eliminates variational inference. The update is naturally permutation-invariant, allowing GLiBRL to integrate with both off- and on-policy algorithms. GLiBRL also learns task representation admitting an exact kernel identity, relating distances between task representations to kernel discrepancies over the task contexts. Compared against eight representative or recent meta reinforcement learning methods, GLiBRL achieves the highest aggregate zero-shot test performance on both the MuJoCo locomotion and MetaWorld manipulation benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 26 of its 39 references that are in the map. First posted on arXiv 24 Dec 2025.

Builds on

26 of 39 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  6. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  7. 2015Generating Sentences from a Continuous Spacecited by 612
  8. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  9. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  10. 2016Learning to reinforcement learncited by 377
  11. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  12. 2013(More) Efficient Reinforcement Learning via Posterior Samplingcited by 233
14 more
  1. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  2. 2018Inference Suboptimality in Variational Autoencoderscited by 132
  3. 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 70
  4. 2024Variational Bayesian Last Layerscited by 69
  5. 2019The Usual Suspects? Reassessing Blame for VAE Posterior Collapsecited by 52
  6. 2018Meta-Learning Priors for Efficient Online Bayesian Regressioncited by 48
  7. 2025Meta-World+: An Improved, Standardized, RL Benchmarkcited by 43
  8. 2022Hypernetworks in Meta-Reinforcement Learningcited by 42
  9. 2022Transformers are Meta-Reinforcement Learnerscited by 41
  10. 2023AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agentscited by 41
  11. 2017Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processescited by 29
  12. 2020Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trialscited by 20
  13. 2019Single Episode Policy Transfer in Reinforcement Learningcited by 18
  14. 2024Disentangling Mean Embeddings for Better Diagnostics of Image Generatorscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025TIMRL: A Novel Meta-Reinforcement Learning Framework for Non-Stationary and Multi-Task Environments
  2. 2023Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills
  3. 2025Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning
  4. 2021Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL
  5. 2025Sample-efficient and Scalable Exploration in Continuous-Time RL
  6. 2023Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models
  7. 2026GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo
  8. 2025Context Representation via Action-Free Transformer encoder-decoder for Meta Reinforcement Learning