Overcooked

'Overcooked' is a benchmark that contains cooperative multi-agent scenarios used to evaluate the reasoning capabilities of agents in decentralized partially observable Markov decision processes (Dec-POMDPs).

Papers using Overcooked (15)

Zero Shot Coordination For Sparse Reward Tasks With Diverse Reward Shapings2026Probing Dec-pomdp Reasoning In Cooperative MARL2026Theory of Mind Guided Strategy Adaptation for Zero-Shot Coordination2026Zero-Shot Coordination in Ad Hoc Teams with Generalized Policy Improvement and Difference Rewards2025Modulation Of Temporal Decision-making In A Deep Reinforcement Learning Agent Under The Dual-task Paradigm2025HDDLGym: A Tool for Studying Multi-Agent Hierarchical Problems Defined in HDDL with OpenAI Gym2025 · 1 citesFixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning2025Learning to Cooperate with Humans using Generative Agents2024 · 1 citesBCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordination2024Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactions2024Learning to Assist Humans without Inferring Rewards2024NiceWebRL: a Python library for human subject experiments with reinforcement learning environments2025Modulation of temporal decision-making in a deep reinforcement learning agent under the dual-task paradigm2025Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning2025Probing Dec-POMDP Reasoning in Cooperative MARL2026