mlsanityData to 14 Oct 2026

Multi-CALF: A Policy Combination Approach with Statistical Guarantees

arXiv 2505.12350 ↗First posted 18 May 2025cs.LG cs.AI cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

We introduce Multi-CALF, an algorithm that intelligently combines reinforcement learning policies based on their relative value improvements. Our approach integrates a standard RL policy with a theoretically-backed alternative policy, inheriting formal stability guarantees while often achieving better performance than either policy individually. We prove that our combined policy converges to a specified goal set with known probability and provide precise bounds on maximum deviation and convergence time. Empirical validation on control tasks demonstrates enhanced performance while maintaining stability guarantees.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 27 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

10 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent15 Sep

Other references · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  5. 2019Solving Rubik's Cube with a Robot Handcited by 734
  6. 2015Policy Distillationcited by 440
  7. 2017Distral: Robust Multitask Reinforcement Learningcited by 233
  8. 2022Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemblecited by 18
  9. 2017Learning to Compose Skillscited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
  2. 2025Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
  3. 2025R2L: Reliable Reinforcement Learning: Guaranteed Return & Reliable Policies in Reinforcement Learning
  4. 2022On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency
  5. 2025A universal policy wrapper with guarantees
  6. 2024A General Control-Theoretic Approach for Reinforcement Learning: Theory and Algorithms
  7. 2025Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization
  8. 2026Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL