{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-view-on-learning-robust-goal-conditioned","title":"A view on learning robust goal-conditioned value functions: Interplay between RL and MPC","arxiv_id":"2502.06996","date":"2025-02-10","proceeding":null,"authors":["Nathan P. Lawrence","Philip D. Loewen","Michael G. Forbes","R. Bhushan Gopaluni","Ali Mesbah"],"abstract":"Reinforcement learning (RL) and model predictive control (MPC) offer a wealth of distinct approaches for automatic decision-making. 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.","url_abs":"https://arxiv.org/abs/2502.06996v1","url_pdf":"https://arxiv.org/pdf/2502.06996v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-view-on-learning-robust-goal-conditioned","repo_url":"https://github.com/NPLawrence/RL-MPC","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model-predictive-control","task_name":"Model Predictive Control"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}