MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via
Mixing Recurrent Soft Decision Trees
- URL: http://arxiv.org/abs/2209.07225v3
- Date: Sun, 14 Jan 2024 10:55:39 GMT
- Title: MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via
Mixing Recurrent Soft Decision Trees
- Authors: Zichuan Liu, Yuanyang Zhu, Zhi Wang, Yang Gao, Chunlin Chen
- Abstract summary: Multi-agent reinforcement learning (MARL) with a black-box neural network architecture makes decisions in an opaque manner.
Existing interpretable approaches, such as traditional linear models and decision trees, usually suffer from weak expressivity and low accuracy.
We develop a novel interpretable architecture that can represent explicit decision processes via the root-to-leaf path.
- Score: 18.83056365359009
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While achieving tremendous success in various fields, existing multi-agent
reinforcement learning (MARL) with a black-box neural network architecture
makes decisions in an opaque manner that hinders humans from understanding the
learned knowledge and how input observations influence decisions. Instead,
existing interpretable approaches, such as traditional linear models and
decision trees, usually suffer from weak expressivity and low accuracy. To
address this apparent dichotomy between performance and interpretability, our
solution, MIXing Recurrent soft decision Trees (MIXRTs), is a novel
interpretable architecture that can represent explicit decision processes via
the root-to-leaf path and reflect each agent's contribution to the team.
Specifically, we construct a novel soft decision tree to address partial
observability by leveraging the advances in recurrent neural networks, and
demonstrate which features influence the decision-making process through the
tree-based model. Then, based on the value decomposition framework, we linearly
assign credit to each agent by explicitly mixing individual action values to
estimate the joint action value using only local observations, providing new
insights into how agents cooperate to accomplish the task. Theoretical analysis
shows that MIXRTs guarantees the structural constraint on additivity and
monotonicity in the factorization of joint action values. Evaluations on the
challenging Spread and StarCraft II tasks show that MIXRTs achieves competitive
performance compared to widely investigated methods and delivers more
straightforward explanations of the decision processes. We explore a promising
path toward developing learning algorithms with both high performance and
interpretability, potentially shedding light on new interpretable paradigms for
MARL.
Related papers
- SynthTree: Co-supervised Local Model Synthesis for Explainable Prediction [15.832975722301011]
We propose a novel method to enhance explainability with minimal accuracy loss.
We have developed novel methods for estimating nodes by leveraging AI techniques.
Our findings highlight the critical role that statistical methodologies can play in advancing explainable AI.
arXiv Detail & Related papers (2024-06-16T14:43:01Z) - A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and
Probabilistic Decision Making [42.503612515214044]
Multi-agent reinforcement learning (MARL) is well-suited for runtime decision-making in systems where multiple agents coexist and compete for shared resources.
Applying common deep learning-based MARL solutions to real-world problems suffers from issues of interpretability, sample efficiency, partial observability, etc.
We present an event-driven formulation, where decision-making is handled by distributed co-operative MARL agents using neuro-symbolic methods.
arXiv Detail & Related papers (2024-02-21T00:16:08Z) - Learning Interpretable Deep Disentangled Neural Networks for
Hyperspectral Unmixing [16.02193274044797]
We propose a new interpretable deep learning method for hyperspectral unmixing that accounts for nonlinearity and endmember variability.
The model is learned end-to-end using backpropagation, and trained using a self-supervised strategy.
Experimental results on synthetic and real datasets illustrate the performance of the proposed method.
arXiv Detail & Related papers (2023-10-03T18:21:37Z) - Latent Variable Representation for Reinforcement Learning [131.03944557979725]
It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning.
We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle.
In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
arXiv Detail & Related papers (2022-12-17T00:26:31Z) - Relational Reasoning via Set Transformers: Provable Efficiency and
Applications to MARL [154.13105285663656]
A cooperative Multi-A gent R einforcement Learning (MARL) with permutation invariant agents framework has achieved tremendous empirical successes in real-world applications.
Unfortunately, the theoretical understanding of this MARL problem is lacking due to the curse of many agents and the limited exploration of the relational reasoning in existing works.
We prove that the suboptimality gaps of the model-free and model-based algorithms are independent of and logarithmic in the number of agents respectively, which mitigates the curse of many agents.
arXiv Detail & Related papers (2022-09-20T16:42:59Z) - On the Complexity of Adversarial Decision Making [101.14158787665252]
We show that the Decision-Estimation Coefficient is necessary and sufficient to obtain low regret for adversarial decision making.
We provide new structural results that connect the Decision-Estimation Coefficient to variants of other well-known complexity measures.
arXiv Detail & Related papers (2022-06-27T06:20:37Z) - Efficient Model-based Multi-agent Reinforcement Learning via Optimistic
Equilibrium Computation [93.52573037053449]
H-MARL (Hallucinated Multi-Agent Reinforcement Learning) learns successful equilibrium policies after a few interactions with the environment.
We demonstrate our approach experimentally on an autonomous driving simulation benchmark.
arXiv Detail & Related papers (2022-03-14T17:24:03Z) - Exploring layerwise decision making in DNNs [1.766593834306011]
We show that by encoding the discrete sample activation values of nodes as a binary representation, we are able to extract a decision tree.
We then combine these decision trees with existing feature attribution techniques in order to produce an interpretation of each layer of a model.
arXiv Detail & Related papers (2022-02-01T11:38:59Z) - Multi-Modal Mutual Information Maximization: A Novel Approach for
Unsupervised Deep Cross-Modal Hashing [73.29587731448345]
We propose a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH)
We learn informative representations that can preserve both intra- and inter-modal similarities.
The proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.
arXiv Detail & Related papers (2021-12-13T08:58:03Z) - Cooperative Policy Learning with Pre-trained Heterogeneous Observation
Representations [51.8796674904734]
We propose a new cooperative learning framework with pre-trained heterogeneous observation representations.
We employ an encoder-decoder based graph attention to learn the intricate interactions and heterogeneous representations.
arXiv Detail & Related papers (2020-12-24T04:52:29Z) - Genetic Adversarial Training of Decision Trees [6.85316573653194]
We put forward a novel learning methodology for ensembles of decision trees based on a genetic algorithm which is able to train a decision tree for maximizing its accuracy and its robustness to adversarial perturbations.
We implemented this genetic adversarial training algorithm in a tool called Meta-Silvae (MS) and we experimentally evaluated it on some reference datasets used in adversarial training.
arXiv Detail & Related papers (2020-12-21T14:05:57Z)
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.