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

• URL: http://arxiv.org/abs/2404.01131v2
• Date: Sun, 14 Apr 2024 19:54:33 GMT
• Title: GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems
• Authors: Ashish Rana, Michael Oesterle, Jannik Brinkmann,
• Abstract summary: We propose GOVerned Reward Engineering Kernels (GOV-REK), which dynamically assign reward distributions to agents in multi-agent reinforcement learning systems. We also introduce governance kernels, which exploit the underlying structure in either state or joint action space for assigning meaningful agent reward distributions. Our experiments demonstrate that our meaningful reward priors robustly jumpstart the learning process for effectively learning different MARL problems.
• Score: 2.867517731896504
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning [56.26889258704261]
  We propose a novel "disentangled" decision-making method, Semantically Aligned task decomposition in MARL (SAMA) SAMA prompts pretrained language models with chain-of-thought that can suggest potential goals, provide suitable goal decomposition and subgoal allocation as well as self-reflection-based replanning. SAMA demonstrates considerable advantages in sample efficiency compared to state-of-the-art ASG methods.
  arXiv  Detail & Related papers  (2023-05-18T10:37:54Z)
• Learning Reward Machines in Cooperative Multi-Agent Tasks [75.79805204646428]
  This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) It combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps deal with the non-Markovian nature of the rewards in partially observable environments.
  arXiv  Detail & Related papers  (2023-03-24T15:12:28Z)
• Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning [19.788336796981685]
  We propose a novel Distributional Reward Estimation framework for effective Multi-Agent Reinforcement Learning (DRE-MARL) Our main idea is to design the multi-action-branch reward estimation and policy-weighted reward aggregation for stabilized training. The superiority of the DRE-MARL is demonstrated using benchmark multi-agent scenarios, compared with the SOTA baselines in terms of both effectiveness and robustness.
  arXiv  Detail & Related papers  (2022-10-14T08:31:45Z)
• Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control [9.118706387430883]
  Reinforcement learning (RL) has recently proven great success in various domains. Yet, the design of the reward function requires detailed domain expertise and tedious fine-tuning to ensure that agents are able to learn the desired behaviour. We propose to use model predictive control(MPC) as an experience source for training RL agents in sparse reward environments.
  arXiv  Detail & Related papers  (2022-10-04T11:06:38Z)
• Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies [64.2210390071609]
  We present a novel Heavy-Tailed Policy Gradient (HT-PSG) algorithm to deal with the challenges of sparse rewards in continuous control problems. We show consistent performance improvement across all tasks in terms of high average cumulative reward.
  arXiv  Detail & Related papers  (2022-06-12T04:09:39Z)
• Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach [130.9259586568977]
  We propose novel learning algorithms to recover the dynamic Vickrey-Clarke-Grove (VCG) mechanism over multiple rounds of interaction. A key contribution of our approach is incorporating reward-free online Reinforcement Learning (RL) to aid exploration over a rich policy space.
  arXiv  Detail & Related papers  (2022-02-25T16:17:23Z)
• Learning Long-Term Reward Redistribution via Randomized Return Decomposition [18.47810850195995]
  We consider the problem formulation of episodic reinforcement learning with trajectory feedback. It refers to an extreme delay of reward signals, in which the agent can only obtain one reward signal at the end of each trajectory. We propose a novel reward redistribution algorithm, randomized return decomposition (RRD), to learn a proxy reward function for episodic reinforcement learning.
  arXiv  Detail & Related papers  (2021-11-26T13:23:36Z)
• Decentralized Multi-Agent Reinforcement Learning for Task Offloading Under Uncertainty [24.083871784808473]
  Multi-Agent Reinforcement Learning (MARL) is a challenging subarea of Reinforcement Learning. Deep MARL algorithms have been applied to solve different task offloading problems. We show that perturbations in the reward signal can induce decrease in the performance compared to learning with perfect rewards.
  arXiv  Detail & Related papers  (2021-07-16T20:49:30Z)
• MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning [65.52675802289775]
  We show that an uncertainty aware classifier can solve challenging reinforcement learning problems. We propose a novel method for computing the normalized maximum likelihood (NML) distribution. We show that the resulting algorithm has a number of intriguing connections to both count-based exploration methods and prior algorithms for learning reward functions.
  arXiv  Detail & Related papers  (2021-07-15T08:19:57Z)
• Softmax with Regularization: Better Value Estimation in Multi-Agent Reinforcement Learning [72.28520951105207]
  Overestimation in $Q$-learning is an important problem that has been extensively studied in single-agent reinforcement learning. We propose a novel regularization-based update scheme that penalizes large joint action-values deviating from a baseline. We show that our method provides a consistent performance improvement on a set of challenging StarCraft II micromanagement tasks.
  arXiv  Detail & Related papers  (2021-03-22T14:18:39Z)
• Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward [0.0]
  We present Decomposed Multi-Agent Deep Deterministic Policy Gradient (DE-MADDPG), a novel cooperative multi-agent reinforcement learning framework. We show that our solution achieves a significantly better and more stable performance than the direct adaptation of the MADDPG algorithm.
  arXiv  Detail & Related papers  (2020-03-24T00:55:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.