RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
The starcraft multi-agent challenge,
24 Pith papers cite this work. Polarity classification is still indexing.
24
Pith papers citing it
citation-role summary
background 2
method 1
other 1
citation-polarity summary
representative citing papers
IBAL framework constructs information-theoretic adversarial attacks on agent observations and actions to train MARL agents that remain robust to interaction disruptions and agent-missing scenarios.
EntCollabBench shows that today's LLM agents still struggle with delegation, context transfer, parameter grounding, workflow closure, and decision commitment when tested in a simulated enterprise with 11 role-specialized agents.
CoFlow achieves state-of-the-art coordination in offline MARL using single-pass joint velocity fields with Coordinated Velocity Attention and Adaptive Coordination Gating.
CLOVER augments value decomposition with a GNN mixer whose weights depend on the realized wireless communication graph, proving permutation invariance, monotonicity, and greater expressiveness than QMIX while showing gains on Predator-Prey and Lumberjacks under p-CSMA channels.
A guided VAE trained on pro StarCraft replays enables four latent-space traversal strategies to produce counterfactual improvement trajectories for amateur players.
IBTS framework uses influence shaping to improve zero-shot human-machine teaming beyond partner diversity alone, with gains shown in Overcooked-AI simulations and a 30-subject human study.
SACHI enriches agent representations via graph transformer convolutions over inter-agent graphs to enable holistic information integration, outperforming baselines across five cooperative tasks with statistical significance.
Interactive IRL is cast as bi-level optimization with an inner loop learning expert rewards and an outer loop learning interaction policies, solved by the convergent BISIRL algorithm.
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
VGM²P achieves SOTA-comparable performance in offline MARL via value-guided conditional behavior cloning with MeanFlow, enabling efficient single-step action generation insensitive to regularization coefficients.
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
CL-MARL uses an adaptive curriculum scheduler called FlexDiff and Counterfactual Group Relative Policy Advantage to break static-difficulty training in MARL and achieve higher win rates on hard StarCraft maps.
VS-Bench is a new benchmark of ten visual multi-agent environments that measures VLMs on element recognition, next-action prediction, and normalized episode return, showing strong perception but large gaps in reasoning and decision-making with the best model at 46.6% prediction accuracy and 31.4% of
Optimistic ε-Greedy Exploration adds decoupled optimistic networks that converge in probability to maximum returns and samples from them with probability ε to increase optimal joint-action frequency in CTDE MARL.
Wolfpack attack framework disrupts MARL cooperation by targeting initial and assisting agents; WALL trains robust policies against it with reported experimental gains.
GACG infers a coordination graph capturing both pair and group dependencies for information exchange in MARL, adds a group distance loss for consistency, and reports superior performance on StarCraft II micromanagement tasks.
Arena introduces a modular Interface design that extends OpenAI Gym wrappers to support complex multi-agent RL scenarios including self-play and cooperative-competitive interactions.
A C++ Dec-POMDP simulator using data-oriented design and zero-copy PyTorch integration achieves up to 33 million steps per second on a 16-core CPU, enabling multi-agent policy training in minutes with PPO, DQN, and SAC.
DAC models fully decentralized cooperative MARL as a context modeling problem, using latent variables for joint policies to fix non-stationarity in value updates and relative overgeneralization in value estimation.
The Focusing Influence Mechanism (FIM) uses an entropy-based criterion and eligibility traces to help multiple agents in reinforcement learning focus and maintain their influence on under-explored parts of the state space, improving coordinated exploration and performance under sparse rewards.
EMTC adds temporal consistency to episodic memory in MARL via contrastive time-conditioned embeddings and dynamic gating, backed by an error bound and yielding up to 24% win-rate gains on hard SMAC and 28% on GRF.
PIMbot introduces an adaptive attack using reward-channel and policy manipulation to disrupt cooperation in multi-robot social dilemma RL, shown effective in Gazebo simulation and on NVIDIA Jetson hardware.
citing papers explorer
-
VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
VS-Bench is a new benchmark of ten visual multi-agent environments that measures VLMs on element recognition, next-action prediction, and normalized episode return, showing strong perception but large gaps in reasoning and decision-making with the best model at 46.6% prediction accuracy and 31.4% of