# Learning from the Hindsight Plan -- Episodic MPC Improvement

arXiv: https://arxiv.org/abs/1609.09001 · HTML: https://mlsanity.com/paper/1609.09001/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2016.

## Built on by (most cited first, 16 of 16)

- [Safe Reinforcement Learning by Imagining the Near Future](https://mlsanity.com/paper/2202.07789/) (2022)
- [Offline Meta-Reinforcement Learning for Industrial Insertion](https://mlsanity.com/paper/2110.04276/) (2021)
- [Learning to Optimize in Model Predictive Control](https://mlsanity.com/paper/2212.02603/) (2022)
- [Learning Sampling Distributions for Model Predictive Control](https://mlsanity.com/paper/2212.02587/) (2022)
- [Graph Reinforcement Learning for Network Control via Bi-Level Optimization](https://mlsanity.com/paper/2305.09129/) (2023)
- [Deep Model Predictive Optimization](https://mlsanity.com/paper/2310.04590/) (2023)
- [A view on learning robust goal-conditioned value functions: Interplay between RL and MPC](https://mlsanity.com/paper/2502.06996/) (2025)
- [The Value of Reward Lookahead in Reinforcement Learning](https://mlsanity.com/paper/2403.11637/) (2024)
- [Learning-Aided Warmstart of Model Predictive Control in Uncertain Fast-Changing Traffic](https://mlsanity.com/paper/2310.02918/) (2023)
- [Learning Multiple Initial Solutions to Optimization Problems](https://mlsanity.com/paper/2411.02158/) (2024)
- [On the Hardness of Reinforcement Learning with Transition Look-Ahead](https://mlsanity.com/paper/2510.19372/) (2025)
- [Generative AI for Autonomous Driving: A Review](https://mlsanity.com/paper/2505.15863/) (2025)
- [Leveraging Experience in Lazy Search](https://mlsanity.com/paper/2110.04669/) (2021)
- [Neural-Progressive Hedging: Enforcing Constraints in Reinforcement Learning with Stochastic Programming](https://mlsanity.com/paper/2202.13436/) (2022)
- [Online Tool Selection with Learned Grasp Prediction Models](https://mlsanity.com/paper/2302.07940/) (2023)
- [Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching](https://mlsanity.com/paper/2601.10418/) (2026)

## Abstract (arXiv)

Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time constraints and often also for robustness to potential model errors. However, the limited horizon leads to suboptimal performance. In this work, we consider the iterative learning setting, where the same task can be repeated several times, and propose a policy improvement scheme for MPC. The main idea is that between executions we can, offline, run MPC with a longer horizon, resulting in a hindsight plan. To bring the next real-world execution closer to the hindsight plan, our approach learns to re-shape the original cost function with the goal of satisfying the following property: short horizon planning (as realistic during real executions) with respect to the shaped cost should result in mimicking the hindsight plan. This effectively consolidates long-term reasoning into the short-horizon planning. We empirically evaluate our approach in contact-rich manipulation tasks both in simulated and real environments, such as peg insertion by a real PR2 robot.