# A Multi-Objective Deep Reinforcement Learning Framework

arXiv: https://arxiv.org/abs/1803.02965 · HTML: https://mlsanity.com/paper/1803.02965/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2018.

## Built on by (most cited first, 23 of 23)

- [A Practical Guide to Multi-Objective Reinforcement Learning and Planning](https://mlsanity.com/paper/2103.09568/) (2021)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain](https://mlsanity.com/paper/2109.06668/) (2021)
- [Levels of explainable artificial intelligence for human-aligned conversational explanations](https://mlsanity.com/paper/2107.03178/) (2021)
- [Two-Stage Constrained Actor-Critic for Short Video Recommendation](https://mlsanity.com/paper/2302.01680/) (2023)
- [Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art](https://mlsanity.com/paper/2412.01566/) (2024)
- [Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning](https://mlsanity.com/paper/2310.02360/) (2023)
- [Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance](https://mlsanity.com/paper/2411.18195/) (2024)
- [Flexible Multiple-Objective Reinforcement Learning for Chip Placement](https://mlsanity.com/paper/2204.06407/) (2022)
- [Loops On Retrieval Augmented Generation (LoRAG)](https://mlsanity.com/paper/2403.15450/) (2024)
- [Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading](https://mlsanity.com/paper/2203.04579/) (2022)
- [Constrained Reinforcement Learning for Short Video Recommendation](https://mlsanity.com/paper/2205.13248/) (2022)
- [GraMeR: Graph Meta Reinforcement Learning for Multi-Objective Influence Maximization](https://mlsanity.com/paper/2205.14834/) (2022)
- [From Intents to Actions: Agentic AI in Autonomous Networks](https://mlsanity.com/paper/2602.01271/) (2026)
- [A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark](https://mlsanity.com/paper/2110.06742/) (2021)
- [gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2204.04988/) (2022)
- [Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning](https://mlsanity.com/paper/2211.04813/) (2022)
- [Reinforcement Learning Agent Design and Optimization with Bandwidth Allocation Model](https://mlsanity.com/paper/2211.12987/) (2022)
- [MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search](https://mlsanity.com/paper/2407.15476/) (2024)
- [Closing the Intent-to-Behavior Gap via Fulfillment Priority Logic](https://mlsanity.com/paper/2503.05818/) (2025)
- [Benchmarking MOEAs for solving continuous multi-objective RL problems](https://mlsanity.com/paper/2505.13726/) (2025)
- [Context-Aware Agentic Power Resources Optimisation in EV using Smart2ChargeApp](https://mlsanity.com/paper/2512.12048/) (2025)
- [Quantum-Inspired Reinforcement Learning for Secure and Sustainable AIoT-Driven Supply Chain Systems](https://mlsanity.com/paper/2601.22339/) (2026)

## Abstract (arXiv)

This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental results on two benchmark problems (two-objective deep sea treasure environment and three-objective Mountain Car problem) indicate that the proposed framework is able to find the Pareto-optimal solutions effectively. The proposed framework is generic and highly modularized, which allows the integration of different deep reinforcement learning algorithms in different complex problem domains. This therefore overcomes many disadvantages involved with standard multi-objective reinforcement learning methods in the current literature. The proposed framework acts as a testbed platform that accelerates the development of MODRL for solving increasingly complicated multi-objective problems.