On Stateful Value Factorization in Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2408.15381v2
• Date: Mon, 9 Sep 2024 22:49:17 GMT
• Title: On Stateful Value Factorization in Multi-Agent Reinforcement Learning
• Authors: Enrico Marchesini, Andrea Baisero, Rupali Bhati, Christopher Amato,
• Abstract summary: We introduce Duelmix, a factorization algorithm that learns distinct per-agent utility estimators to improve performance. Experiments on StarCraft II micromanagement and Box Pushing tasks demonstrate the benefits of our intuitions.
• Score: 19.342676562701794
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Value factorization is a popular paradigm for designing scalable multi-agent reinforcement learning algorithms. However, current factorization methods make choices without full justification that may limit their performance. For example, the theory in prior work uses stateless (i.e., history) functions, while the practical implementations use state information -- making the motivating theory a mismatch for the implementation. Also, methods have built off of previous approaches, inheriting their architectures without exploring other, potentially better ones. To address these concerns, we formally analyze the theory of using the state instead of the history in current methods -- reconnecting theory and practice. We then introduce DuelMIX, a factorization algorithm that learns distinct per-agent utility estimators to improve performance and achieve full expressiveness. Experiments on StarCraft II micromanagement and Box Pushing tasks demonstrate the benefits of our intuitions.

Related papers

• ReconBoost: Boosting Can Achieve Modality Reconcilement [89.4377895465204]
  We study the modality-alternating learning paradigm to achieve reconcilement. We propose a new method called ReconBoost to update a fixed modality each time. We show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others.
  arXiv  Detail & Related papers  (2024-05-15T13:22:39Z)
• Efficient and Generalizable Certified Unlearning: A Hessian-free Recollection Approach [8.875278412741695]
  Machine unlearning strives to uphold the data owners' right to be forgotten by enabling models to selectively forget specific data. We develop an algorithm that achieves near-instantaneous unlearning as it only requires a vector addition operation.
  arXiv  Detail & Related papers  (2024-04-02T07:54:18Z)
• RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
  We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
  arXiv  Detail & Related papers  (2023-11-21T21:05:21Z)
• Are Good Explainers Secretly Human-in-the-Loop Active Learners? [0.0]
  Explainable AI (XAI) techniques have become popular for multiple use-cases in the past few years. Here we consider its use in studying model predictions to gather additional training data. We argue that this is equivalent to Active Learning, where the query strategy involves a human-in-the-loop.
  arXiv  Detail & Related papers  (2023-06-24T10:50:42Z)
• Model Predictive Control with Self-supervised Representation Learning [13.225264876433528]
  We propose the use of a reconstruction function within the TD-MPC framework, so that the agent can reconstruct the original observation. Our proposed addition of another loss term leads to improved performance on both state- and image-based tasks.
  arXiv  Detail & Related papers  (2023-04-14T16:02:04Z)
• Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning [105.70602423944148]
  We propose a novel method, called value-consistent representation learning (VCR), to learn representations that are directly related to decision-making. Instead of aligning this imagined state with a real state returned by the environment, VCR applies a $Q$-value head on both states and obtains two distributions of action values. It has been demonstrated that our methods achieve new state-of-the-art performance for search-free RL algorithms.
  arXiv  Detail & Related papers  (2022-06-25T03:02:25Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)
• Revisiting Model-based Value Expansion [35.55280687116388]
  Model-based value expansion methods promise to improve the quality of value function targets and the effectiveness of value function learning. However, to date, these methods are being outperformed by Dyna-style algorithms with conceptually simpler 1-step value function targets. We provide a thorough empirical study to shed light on the causes of failure of value expansion methods in practice.
  arXiv  Detail & Related papers  (2022-03-28T11:21:49Z)
• What can I do here? A Theory of Affordances in Reinforcement Learning [65.70524105802156]
  We develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case, by reducing the number of actions available in any given situation. We propose an approach to learn affordances and use it to estimate transition models that are simpler and generalize better.
  arXiv  Detail & Related papers  (2020-06-26T16:34:53Z)
• An Advance on Variable Elimination with Applications to Tensor-Based Computation [11.358487655918676]
  We present new results on the classical algorithm of variable elimination, which underlies many algorithms including for probabilistic inference. The results relate to exploiting functional dependencies, allowing one to perform inference and learning efficiently on models that have very large treewidth.
  arXiv  Detail & Related papers  (2020-02-21T14:17:44Z)

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.