MPE

Overview Original dataset here. Dataset curation Same data and splits as the original. The following columns have been added: premise: concatenation of premise1, premise2, premise3, and premise4 label: encoded gold_label with the following mapping {"entailment": 0, "neutral": 1, "contradiction": 2} Code to create the d

Papers using MPE (18)

CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution2025 · 3 citesProbing Dec-pomdp Reasoning In Cooperative MARL2026STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement Learning2026Learning Partial Action Replacement in Offline MARL2026Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning2025Multi-party Agent Relation Sampling for Multi-party Ad Hoc Teamwork2025$Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation2025Centralized Permutation Equivariant Policy for Cooperative Multi-Agent Reinforcement Learning2025Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observation2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration2025Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance2024 · 2 citesChoices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration2024Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer2025JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes2025Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies2026Probing Dec-POMDP Reasoning in Cooperative MARL2026Dual-Gated Epistemic Time-Dilation: Autonomous Compute Modulation in Asynchronous MARL2026KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning2026