REVIEW 2 cited by
Explainable Multi-Agent Reinforcement Learning for Temporal Queries
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
As multi-agent reinforcement learning (MARL) systems are increasingly deployed throughout society, it is imperative yet challenging for users to understand the emergent behaviors of MARL agents in complex environments. This work presents an approach for generating policy-level contrastive explanations for MARL to answer a temporal user query, which specifies a sequence of tasks completed by agents with possible cooperation. The proposed approach encodes the temporal query as a PCTL logic formula and checks if the query is feasible under a given MARL policy via probabilistic model checking. Such explanations can help reconcile discrepancies between the actual and anticipated multi-agent behaviors. The proposed approach also generates correct and complete explanations to pinpoint reasons that make a user query infeasible. We have successfully applied the proposed approach to four benchmark MARL domains (up to 9 agents in one domain). Moreover, the results of a user study show that the generated explanations significantly improve user performance and satisfaction.
Forward citations
Cited by 2 Pith papers
-
Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning
Neurons in DRL agents are matched to short Boolean formulas over hand-defined state predicates, with anecdotal perturbation evidence that these matches reflect real behavior.
-
Prioritized Value-Decomposition Network for Explainable AI-Enabled Network Slicing
PVDN adds an adaptive cross-metric reward penalty to VDN for two-slice network resource allocation and reports improved throughput and latency in simulation.
Discussion (0). Continue with ORCID to comment.