mlsanityData to 7 Oct 2026

GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems

arXiv 2404.01131 ↗First posted 1 Apr 2024cs.MA cs.AIcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

Abstract (arXiv)

For multi-agent reinforcement learning systems (MARLS), the problem formulation generally involves investing massive reward engineering effort specific to a given problem. However, this effort often cannot be translated to other problems; worse, it gets wasted when system dynamics change drastically. This problem is further exacerbated in sparse reward scenarios, where a meaningful heuristic can assist in the policy convergence task. We propose GOVerned Reward Engineering Kernels (GOV-REK), which dynamically assign reward distributions to agents in MARLS during its learning stage. We also introduce governance kernels, which exploit the underlying structure in either state or joint action space for assigning meaningful agent reward distributions. During the agent learning stage, it iteratively explores different reward distribution configurations with a Hyperband-like algorithm to learn ideal agent reward models in a problem-agnostic manner. Our experiments demonstrate that our meaningful reward priors robustly jumpstart the learning process for effectively learning different MARL problems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 16 of its 51 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

16 of 51 references.

References · 16

  1. 2018Exploration by Random Network Distillationcited by 966
  2. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  3. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  4. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  5. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
  6. 2020Agent57: Outperforming the Atari Human Benchmarkcited by 300
  7. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
  8. 2017Count-Based Exploration with Neural Density Modelscited by 255
  9. 2020Never Give Up: Learning Directed Exploration Strategiescited by 210
  10. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 206
  11. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
  12. 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 114
4 more
  1. 2015Sample Complexity of Episodic Fixed-Horizon Reinforcement Learningcited by 105
  2. 2020Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learningcited by 47
  3. 2017A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agentscited by 18
  4. 2022Reinforcement Learning Guided by Provable Normative Compliancecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning
  2. 2018Scalable agent alignment via reward modeling: a research direction
  3. 2026Reward-rate Policy Gradient for Efficient Machine Learning Engineering Agents
  4. 2026The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination
  5. 2026Multi-Agent Reinforcement Learning via Agent-Specific Preference
  6. 2025Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
  7. 2025Reward Models in Deep Reinforcement Learning: A Survey
  8. 2025ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning