Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.06996 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911202064465920 |
|---|---|
| author | Lawrence, Nathan P. Loewen, Philip D. Forbes, Michael G. Gopaluni, R. Bhushan Mesbah, Ali |
| author_facet | Lawrence, Nathan P. Loewen, Philip D. Forbes, Michael G. Gopaluni, R. Bhushan Mesbah, Ali |
| contents | Reinforcement learning (RL) and model predictive control (MPC) offer a wealth of distinct approaches for automatic decision-making under uncertainty. Given the impact both fields have had independently across numerous domains, there is growing interest in combining the general-purpose learning capability of RL with the safety and robustness features of MPC. To this end, this paper presents a tutorial-style treatment of RL and MPC, treating them as alternative approaches to solving Markov decision processes. In our formulation, RL aims to learn a global value function through offline exploration in an uncertain environment, whereas MPC constructs a local value function through online optimization. This local-global perspective suggests new ways to design policies that combine robustness and goal-conditioned learning. Robustness is incorporated into the RL and MPC pipelines through a scenario-based approach. Goal-conditioned learning aims to alleviate the burden of engineering a reward function for RL. Combining the two leads to a single policy that unites a robust, high-level RL terminal value function with short-term, scenario-based MPC planning for reliable constraint satisfaction. This approach leverages the benefits of both RL and MPC, the effectiveness of which is demonstrated on classical control benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06996 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A view on learning robust goal-conditioned value functions: Interplay between RL and MPC Lawrence, Nathan P. Loewen, Philip D. Forbes, Michael G. Gopaluni, R. Bhushan Mesbah, Ali Systems and Control Reinforcement learning (RL) and model predictive control (MPC) offer a wealth of distinct approaches for automatic decision-making under uncertainty. Given the impact both fields have had independently across numerous domains, there is growing interest in combining the general-purpose learning capability of RL with the safety and robustness features of MPC. To this end, this paper presents a tutorial-style treatment of RL and MPC, treating them as alternative approaches to solving Markov decision processes. In our formulation, RL aims to learn a global value function through offline exploration in an uncertain environment, whereas MPC constructs a local value function through online optimization. This local-global perspective suggests new ways to design policies that combine robustness and goal-conditioned learning. Robustness is incorporated into the RL and MPC pipelines through a scenario-based approach. Goal-conditioned learning aims to alleviate the burden of engineering a reward function for RL. Combining the two leads to a single policy that unites a robust, high-level RL terminal value function with short-term, scenario-based MPC planning for reliable constraint satisfaction. This approach leverages the benefits of both RL and MPC, the effectiveness of which is demonstrated on classical control benchmarks. |
| title | A view on learning robust goal-conditioned value functions: Interplay between RL and MPC |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2502.06996 |