# Multi-CALF: A Policy Combination Approach with Statistical Guarantees

arXiv: https://arxiv.org/abs/2505.12350 · HTML: https://mlsanity.com/paper/2505.12350/

## 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.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 10 of 10)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Distral: Robust Multitask Reinforcement Learning](https://mlsanity.com/paper/1707.04175/) (2017)
- [Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble](https://mlsanity.com/paper/2205.09284/) (2022)
- [Learning to Compose Skills](https://mlsanity.com/paper/1711.11289/) (2017)
- [Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent](https://mlsanity.com/paper/2409.09869/) (2024)

## 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.