Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.10608 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908489987653632 |
|---|---|
| author | Guidobene, Davide Benedetti, Lorenzo Arapovic, Diego |
| author_facet | Guidobene, Davide Benedetti, Lorenzo Arapovic, Diego |
| contents | Multi-Objective Reinforcement Learning (MORL) is a generalization of traditional Reinforcement Learning (RL) that aims to optimize multiple, often conflicting objectives simultaneously rather than focusing on a single reward. This approach is crucial in complex decision-making scenarios where agents must balance trade-offs between various goals, such as maximizing performance while minimizing costs. We consider the problem of MORL where the objectives are combined using a non-linear scalarization function. Just like in standard RL, policy gradient methods (PGMs) are amongst the most effective for handling large and continuous state-action spaces in MORL. However, existing PGMs for MORL suffer from high sample inefficiency, requiring large amounts of data to be effective. Previous attempts to solve this problem rely on overly strict assumptions, losing PGMs' benefits in scalability to large state-action spaces. In this work, we address the issue of sample efficiency by implementing variance-reduction techniques to reduce the sample complexity of policy gradients while maintaining general assumptions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10608 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Variance Reduced Policy Gradient Method for Multi-Objective Reinforcement Learning Guidobene, Davide Benedetti, Lorenzo Arapovic, Diego Machine Learning Systems and Control Optimization and Control Statistics Theory 68T05: 90C26: 90C40 I.2.0; G.3 Multi-Objective Reinforcement Learning (MORL) is a generalization of traditional Reinforcement Learning (RL) that aims to optimize multiple, often conflicting objectives simultaneously rather than focusing on a single reward. This approach is crucial in complex decision-making scenarios where agents must balance trade-offs between various goals, such as maximizing performance while minimizing costs. We consider the problem of MORL where the objectives are combined using a non-linear scalarization function. Just like in standard RL, policy gradient methods (PGMs) are amongst the most effective for handling large and continuous state-action spaces in MORL. However, existing PGMs for MORL suffer from high sample inefficiency, requiring large amounts of data to be effective. Previous attempts to solve this problem rely on overly strict assumptions, losing PGMs' benefits in scalability to large state-action spaces. In this work, we address the issue of sample efficiency by implementing variance-reduction techniques to reduce the sample complexity of policy gradients while maintaining general assumptions. |
| title | Variance Reduced Policy Gradient Method for Multi-Objective Reinforcement Learning |
| topic | Machine Learning Systems and Control Optimization and Control Statistics Theory 68T05: 90C26: 90C40 I.2.0; G.3 |
| url | https://arxiv.org/abs/2508.10608 |