# Learning to recover: Adaptive local branching with reinforcement learning for log-truck routing and scheduling under disruptions

arXiv: https://arxiv.org/abs/2607.20901 · HTML: https://mlsanity.com/paper/2607.20901/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods.
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Placed in

- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Survey of Multi-Objective Sequential Decision-Making](https://mlsanity.com/paper/1402.0590/) (2014)
- [Reinforcement Learning for Integer Programming: Learning to Cut](https://mlsanity.com/paper/1906.04859/) (2019)
- [PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm](https://mlsanity.com/paper/2208.07914/) (2022)
- [Vehicle Routing with Stochastic Demands and Partial Reoptimization](https://mlsanity.com/paper/2201.08866/) (2022)
- [Real-World, Large Scale, Multi-Period Log Truck Routing and Scheduling : Application to Canadian Forestry](https://mlsanity.com/paper/2607.16978/) (2026)

## Abstract (arXiv)

We consider the real-time reoptimisation of log-truck routing and scheduling in the Canadian forestry industry following unforeseen disruptions. Road closures, vehicle breakdowns, travel delays, and demand fluctuations invalidate pre-established tactical plans and call for recovery decisions that simultaneously restore feasibility and limit deviation from the original schedule, two objectives inherently in tension under tight time constraints. We formulate recovery as a sequence of neighbourhood-restricted mixed-integer linear programs parameterised by a deviation bound k, the ℓ1 distance between the recovered and baseline plans. We show that the minimum feasible value kmin can be computed exactly, anchoring the search at its most stable extreme. Rather than targeting a single k, we seek a Pareto front of non-dominated recovery plans spanning the stability--cost space, giving dispatchers a structured set of operational options. To navigate this space efficiently, we propose a reinforcement learning policy, trained with the REINFORCE policy-gradient algorithm, that adaptively selects successive values of k from solver feedback, concentrating computational effort in productive regions and terminating exploration when further improvement is unlikely. Evaluated on weekly instances derived from historical data of a Canadian forestry partner, under disruption scenarios covering all event categories considered, the approach recovers richer Pareto fronts with fewer solver calls than fixed-k grid and dichotomic search baselines, and produces feasible recovery plans within operationally acceptable reoptimization times across all configurations and disruption types.