{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/multi-agent-reinforcement-learning/papers/8","list_of":"/task/multi-agent-reinforcement-learning","task":"Multi-agent Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":8,"pages_in_order":18,"rows_per_page":100,"rows":[701,800],"of":1718,"counts":{"archive_papers_tagged":1718,"with_a_code_link":522,"where_syntology_ran_a_sample":135,"not_listed_spam_title":0,"listed":1718,"listed_where_code_ran":135,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":119,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":119,"listed_every_run_a_failure_of_syntologys_instrument":16,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/multi-agent-reinforcement-learning","prev":"/task/multi-agent-reinforcement-learning/papers/7","next":"/task/multi-agent-reinforcement-learning/papers/9","papers":[{"url":null,"slug":"adversarial-multi-agent-reinforcement","title":"Adversarial Multi-Agent Reinforcement Learning for Proactive False Data Injection Detection","date":"2024-11-19","arxiv_id":"2411.12130","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-training-in-multi-agent","title":"Efficient Training in Multi-Agent Reinforcement Learning: A Communication-Free Framework for the Box-Pushing Problem","date":"2024-11-19","arxiv_id":"2411.12246","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-relative-over-generalization-in","title":"Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning","date":"2024-11-17","arxiv_id":"2411.11099","repositories_listed":0,"syntology":null},{"url":null,"slug":"empathic-coupling-of-homeostatic-states-for","title":"Empathic Coupling of Homeostatic States for Intrinsic Prosociality","date":"2024-11-16","arxiv_id":"2412.12103","repositories_listed":0,"syntology":null},{"url":null,"slug":"enforcing-cooperative-safety-for","title":"Enforcing Cooperative Safety for Reinforcement Learning-based Mixed-Autonomy Platoon Control","date":"2024-11-15","arxiv_id":"2411.10031","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnn-task-assignment-in-uav-networks-a","title":"DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach","date":"2024-11-13","arxiv_id":"2411.08299","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-multi-agent-reinforcement-learning","title":"Exploring Multi-Agent Reinforcement Learning for Unrelated Parallel Machine Scheduling","date":"2024-11-12","arxiv_id":"2411.07634","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-agent-approach-for-rest-api-testing","title":"A Multi-Agent Approach for REST API Testing with Semantic Graphs and LLM-Driven Inputs","date":"2024-11-11","arxiv_id":"2411.07098","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-agent-collaborative","title":"Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing","date":"2024-11-11","arxiv_id":"2411.07104","repositories_listed":0,"syntology":null},{"url":null,"slug":"offlight-an-offline-multi-agent-reinforcement","title":"OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control","date":"2024-11-10","arxiv_id":"2411.06601","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-distributed-common-operational","title":"Data-Driven Distributed Common Operational Picture from Heterogeneous Platforms using Multi-Agent Reinforcement Learning","date":"2024-11-08","arxiv_id":"2411.05683","repositories_listed":0,"syntology":null},{"url":null,"slug":"role-play-learning-adaptive-role-specific","title":"Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactions","date":"2024-11-02","arxiv_id":"2411.01166","repositories_listed":0,"syntology":null},{"url":null,"slug":"anytime-constrained-multi-agent-reinforcement","title":"Anytime-Constrained Equilibria in Polynomial Time","date":"2024-10-31","arxiv_id":"2410.23637","repositories_listed":0,"syntology":null},{"url":null,"slug":"demand-aware-beam-hopping-and-power","title":"Demand-Aware Beam Hopping and Power Allocation for Load Balancing in Digital Twin empowered LEO Satellite Networks","date":"2024-10-29","arxiv_id":"2411.08896","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-aware-multi-agent-reinforcement","title":"Energy-Aware Multi-Agent Reinforcement Learning for Collaborative Execution in Mission-Oriented Drone Networks","date":"2024-10-29","arxiv_id":"2410.22578","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-agent-reinforcement-learning-testbed","title":"A Multi-Agent Reinforcement Learning Testbed for Cognitive Radio Applications","date":"2024-10-28","arxiv_id":"2410.21521","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-9","title":"Multi-Agent Reinforcement Learning with Selective State-Space Models","date":"2024-10-25","arxiv_id":"2410.19382","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-to-online-multi-agent-reinforcement","title":"Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration","date":"2024-10-25","arxiv_id":"2410.19450","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-dispersal-of-ecological-species","title":"Evolutionary Dispersal of Ecological Species via Multi-Agent Deep Reinforcement Learning","date":"2024-10-24","arxiv_id":"2410.18621","repositories_listed":0,"syntology":null},{"url":null,"slug":"convex-markov-games-a-framework-for-fairness","title":"Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.16600","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-future-thinking-mechanism-for-multi","title":"Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.17373","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-multi-agent-reinforcement-2","title":"Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense","date":"2024-10-22","arxiv_id":"2410.17351","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-spectral-representations-for-network","title":"Scalable spectral representations for multi-agent reinforcement learning in network MDPs","date":"2024-10-22","arxiv_id":"2410.17221","repositories_listed":0,"syntology":null},{"url":null,"slug":"flickerfusion-intra-trajectory-domain","title":"FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL","date":"2024-10-21","arxiv_id":"2410.15876","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-distributed-primal-dual-method-for","title":"A Distributed Primal-Dual Method for Constrained Multi-agent Reinforcement Learning with General Parameterization","date":"2024-10-20","arxiv_id":"2410.15335","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-balance-altruism-and-self","title":"Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games","date":"2024-10-10","arxiv_id":"2410.07863","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-inequality-methods-for-multi","title":"Variational Inequality Methods for Multi-Agent Reinforcement Learning: Performance and Stability Gains","date":"2024-10-10","arxiv_id":"2410.07976","repositories_listed":0,"syntology":null},{"url":null,"slug":"cafeen-a-cooperative-approach-for-energy","title":"CAFEEN: A Cooperative Approach for Energy Efficient NoCs with Multi-Agent Reinforcement Learning","date":"2024-10-09","arxiv_id":"2410.07426","repositories_listed":0,"syntology":null},{"url":null,"slug":"last-iterate-convergence-in-monotone-mean","title":"Last Iterate Convergence in Monotone Mean Field Games","date":"2024-10-07","arxiv_id":"2410.05127","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-sample-efficiency-and-generalization","title":"Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance","date":"2024-10-03","arxiv_id":"2410.02581","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-answers-for-multi-agent-decision","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","date":"2024-10-03","arxiv_id":"2410.02664","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-emergence-of-interaction-patterns","title":"Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments","date":"2024-10-03","arxiv_id":"2410.02516","repositories_listed":0,"syntology":null},{"url":null,"slug":"comadice-offline-cooperative-multi-agent","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","date":"2024-10-02","arxiv_id":"2410.01954","repositories_listed":0,"syntology":null},{"url":null,"slug":"performant-memory-efficient-and-scalable","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","date":"2024-10-02","arxiv_id":"2410.01706","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-structure-in-offline-multi-agent","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","date":"2024-10-01","arxiv_id":"2410.01101","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-break-the-curse-of-multiagency-in","title":"Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning","date":"2024-09-30","arxiv_id":"2409.20067","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-multi-robot-collaboration-from","title":"Enabling Multi-Robot Collaboration from Single-Human Guidance","date":"2024-09-30","arxiv_id":"2409.19831","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-based-deep-multi-agent-reinforcement","title":"Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training","date":"2024-09-28","arxiv_id":"2409.19391","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-23","title":"Multi-agent Reinforcement Learning for Dynamic Dispatching in Material Handling Systems","date":"2024-09-27","arxiv_id":"2409.18435","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-uav-pursuit-evasion-with-online","title":"Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning","date":"2024-09-24","arxiv_id":"2409.15866","repositories_listed":0,"syntology":null},{"url":null,"slug":"pathseeker-exploring-llm-security","title":"PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach","date":"2024-09-21","arxiv_id":"2409.14177","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-multi-agent-reinforcement-learning-5","title":"Scalable Multi-agent Reinforcement Learning for Factory-wide Dynamic Scheduling","date":"2024-09-20","arxiv_id":"2409.13571","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-hardness-of-decentralized-multi-agent","title":"On the Hardness of Decentralized Multi-Agent Policy Evaluation under Byzantine Attacks","date":"2024-09-19","arxiv_id":"2409.12882","repositories_listed":0,"syntology":null},{"url":null,"slug":"harp-human-assisted-regrouping-with","title":"HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning","date":"2024-09-18","arxiv_id":"2409.11741","repositories_listed":0,"syntology":null},{"url":null,"slug":"putting-data-at-the-centre-of-offline-multi","title":"Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning","date":"2024-09-18","arxiv_id":"2409.12001","repositories_listed":0,"syntology":null},{"url":null,"slug":"dcmac-demand-aware-customized-multi-agent","title":"DCMAC: Demand-aware Customized Multi-Agent Communication via Upper Bound Training","date":"2024-09-11","arxiv_id":"2409.07127","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-multi-organ-disease-care-a","title":"Advancing Multi-Organ Disease Care: A Hierarchical Multi-Agent Reinforcement Learning Framework","date":"2024-09-06","arxiv_id":"2409.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-emergent-language","title":"Emergent Language: A Survey and Taxonomy","date":"2024-09-04","arxiv_id":"2409.02645","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-introduction-to-centralized-training-for","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","date":"2024-09-04","arxiv_id":"2409.03052","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-for-joint-1","title":"Multi-Agent Reinforcement Learning for Joint Police Patrol and Dispatch","date":"2024-09-03","arxiv_id":"2409.02246","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-path-planning-with-asynchronous","title":"Cooperative Path Planning with Asynchronous Multiagent Reinforcement Learning","date":"2024-09-01","arxiv_id":"2409.00754","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-from-human","title":"Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques","date":"2024-09-01","arxiv_id":"2409.00717","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-agent-multi-machine-tending-by","title":"Learning Multi-agent Multi-machine Tending by Mobile Robots","date":"2024-08-29","arxiv_id":"2408.16875","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-approximate-symmetry-for-efficient","title":"Exploiting Approximate Symmetry for Efficient Multi-Agent Reinforcement Learning","date":"2024-08-27","arxiv_id":"2408.15173","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-stateful-value-factorization-in-multi","title":"On Stateful Value Factorization in Multi-Agent Reinforcement Learning","date":"2024-08-27","arxiv_id":"2408.15381","repositories_listed":0,"syntology":null},{"url":"/paper/hybrid-training-for-enhanced-multi-task","slug":"hybrid-training-for-enhanced-multi-task","title":"Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning","date":"2024-08-24","arxiv_id":"2408.13567","repositories_listed":0,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hybrid-training-for-enhanced-multi-task#ran","syntology_url":"https://syntology.ai/paper/2408.13567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13567"}},"official":null}},{"url":null,"slug":"diffusion-based-episodes-augmentation-for","title":"Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning","date":"2024-08-23","arxiv_id":"2408.13092","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-noncoherent-joint-transmission","title":"Distributed Noncoherent Joint Transmission Based on Multi-Agent Reinforcement Learning for Dense Small Cell MISO Systems","date":"2024-08-22","arxiv_id":"2408.12067","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-local-views-global-state-inference","title":"Beyond Local Views: Global State Inference with Diffusion Models for Cooperative Multi-Agent Reinforcement Learning","date":"2024-08-18","arxiv_id":"2408.09501","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semi-centralized-multi-agent-rl-framework","title":"A semi-centralized multi-agent RL framework for efficient irrigation scheduling","date":"2024-08-15","arxiv_id":"2408.08442","repositories_listed":0,"syntology":null},{"url":null,"slug":"independent-policy-mirror-descent-for-markov","title":"Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players","date":"2024-08-15","arxiv_id":"2408.08075","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-global-parameter-sharing-in","title":"Improving Global Parameter-sharing in Physically Heterogeneous Multi-agent Reinforcement Learning with Unified Action Space","date":"2024-08-14","arxiv_id":"2408.07395","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02148","title":"Environment Complexity and Nash Equilibria in a Sequential Social Dilemma","date":"2024-08-04","arxiv_id":"2408.02148","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01072","title":"A Survey on Self-play Methods in Reinforcement Learning","date":"2024-08-02","arxiv_id":"2408.01072","repositories_listed":0,"syntology":null},{"url":null,"slug":"architectural-influence-on-variational","title":"Architectural Influence on Variational Quantum Circuits in Multi-Agent Reinforcement Learning: Evolutionary Strategies for Optimization","date":"2024-07-30","arxiv_id":"2407.20739","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-uncertainties-in-electricity","title":"Evaluating Uncertainties in Electricity Markets via Machine Learning and Quantum Computing","date":"2024-07-23","arxiv_id":"2407.16404","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-replay-memory-architectures-in","title":"Efficient Replay Memory Architectures in Multi-Agent Reinforcement Learning for Traffic Congestion Control","date":"2024-07-22","arxiv_id":"2407.16034","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-the-smog-a-cooperative-multi-agent","title":"Navigating the Smog: A Cooperative Multi-Agent RL for Accurate Air Pollution Mapping through Data Assimilation","date":"2024-07-17","arxiv_id":"2407.12539","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-collaborative-intelligence-1","title":"Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models","date":"2024-07-17","arxiv_id":"2407.12532","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-reward-shaping-for-multi-agent","title":"Cooperative Reward Shaping for Multi-Agent Pathfinding","date":"2024-07-15","arxiv_id":"2407.10403","repositories_listed":0,"syntology":null},{"url":null,"slug":"ontology-driven-reinforcement-learning-for","title":"Ontology-driven Reinforcement Learning for Personalized Student Support","date":"2024-07-14","arxiv_id":"2407.10332","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-aware-reinforcement-learning","title":"Communication-Aware Reinforcement Learning for Cooperative Adaptive Cruise Control","date":"2024-07-12","arxiv_id":"2407.08964","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-agent-reinforcement-7","title":"Decentralized multi-agent reinforcement learning algorithm using a cluster-synchronized laser network","date":"2024-07-12","arxiv_id":"2407.09124","repositories_listed":0,"syntology":null},{"url":null,"slug":"arco-adaptive-multi-agent-reinforcement","title":"Dynamic Co-Optimization Compiler: Leveraging Multi-Agent Reinforcement Learning for Enhanced DNN Accelerator Performance","date":"2024-07-11","arxiv_id":"2407.08192","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-consensus-based-multi-agent","title":"Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks","date":"2024-07-11","arxiv_id":"2407.08164","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-based-5","title":"Multi-agent Reinforcement Learning-based Network Intrusion Detection System","date":"2024-07-08","arxiv_id":"2407.05766","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-off-policy-actor-critic","title":"Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments","date":"2024-07-06","arxiv_id":"2407.04974","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-the-applications-of-deep-learning","title":"A Review of the Applications of Deep Learning-Based Emergent Communication","date":"2024-07-03","arxiv_id":"2407.03302","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scenario-combination-based-on-multi","title":"Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System","date":"2024-07-03","arxiv_id":"2407.02759","repositories_listed":0,"syntology":null},{"url":null,"slug":"wildfire-autonomous-response-and-prediction","title":"Wildfire Autonomous Response and Prediction Using Cellular Automata (WARP-CA)","date":"2024-07-02","arxiv_id":"2407.02613","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordination-failure-in-cooperative-offline","title":"Coordination Failure in Cooperative Offline MARL","date":"2024-07-01","arxiv_id":"2407.01343","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-models-for-offline-multi-agent","title":"Diffusion Models for Offline Multi-agent Reinforcement Learning with Safety Constraints","date":"2024-06-30","arxiv_id":"2407.00741","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuda2-an-approach-for-incorporating-traitor","title":"CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems","date":"2024-06-25","arxiv_id":"2406.17425","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-multi-agent-reinforcement-learning-3","title":"Quantum Multi-Agent Reinforcement Learning for Cooperative Mobile Access in Space-Air-Ground Integrated Networks","date":"2024-06-24","arxiv_id":"2406.16994","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-digital-twin-and-communication","title":"Adaptive Digital Twin and Communication-Efficient Federated Learning Network Slicing for 5G-enabled Internet of Things","date":"2024-06-22","arxiv_id":"2407.10987","repositories_listed":0,"syntology":null},{"url":null,"slug":"tractable-equilibrium-computation-in-markov","title":"Tractable Equilibrium Computation in Markov Games through Risk Aversion","date":"2024-06-20","arxiv_id":"2406.14156","repositories_listed":0,"syntology":null},{"url":null,"slug":"velo-a-vector-database-assisted-cloud-edge","title":"VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework","date":"2024-06-19","arxiv_id":"2406.13399","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-marl-for-platoon","title":"Communication-Efficient MARL for Platoon Stability and Energy-efficiency Co-optimization in Cooperative Adaptive Cruise Control of CAVs","date":"2024-06-17","arxiv_id":"2406.11653","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-benefits-of-power-regularization-in","title":"The Benefits of Power Regularization in Cooperative Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.11240","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-adaptation-in-mixed-motive","title":"Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning","date":"2024-06-12","arxiv_id":"2406.08002","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-with-deep","title":"Multi-agent Reinforcement Learning with Deep Networks for Diverse Q-Vectors","date":"2024-06-12","arxiv_id":"2406.07848","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-opponent-policy-detection-in-multi","title":"Adaptive Opponent Policy Detection in Multi-Agent MDPs: Real-Time Strategy Switch Identification Using Running Error Estimation","date":"2024-06-10","arxiv_id":"2406.06500","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-sensitivity-in-markov-games-and-multi","title":"Risk Sensitivity in Markov Games and Multi-Agent Reinforcement Learning: A Systematic Review","date":"2024-06-10","arxiv_id":"2406.06041","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-efficient-deep","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.02890","repositories_listed":0,"syntology":null},{"url":null,"slug":"fightladder-a-benchmark-for-competitive-multi","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","date":"2024-06-04","arxiv_id":"2406.02081","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-meets-leaf","title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","date":"2024-06-03","arxiv_id":"2406.01853","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-transfer-learning-via-temporal","title":"Multi-Agent Transfer Learning via Temporal Contrastive Learning","date":"2024-06-03","arxiv_id":"2406.01377","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-psro-nash-policy-fusion-for-policy","title":"Fusion-PSRO: Nash Policy Fusion for Policy Space Response Oracles","date":"2024-05-31","arxiv_id":"2405.21027","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multi-agent-reinforcement-learning-with-1","title":"Safe Multi-agent Reinforcement Learning with Natural Language Constraints","date":"2024-05-30","arxiv_id":"2405.20018","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutation-bias-learning-in-games","title":"Mutation-Bias Learning in Games","date":"2024-05-28","arxiv_id":"2405.18190","repositories_listed":0,"syntology":null}],"record_sha256":"62d227141fc25487c321c2d70fa6bcae52a14021bf227d3a8aa6f89eacdced57","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}