Starcraft II
81 papers with code • 3 benchmarks • 4 datasets
Starcraft II is a RTS game; the task is to train an agent to play the game.
( Image credit: The StarCraft Multi-Agent Challenge )
Libraries
Use these libraries to find Starcraft II models and implementationsLatest papers with no code
Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning
In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentangled World Model to address the challenge of achieving a common goal of multiple agents interacting in the same environment with reduced sample complexity.
Never Explore Repeatedly in Multi-Agent Reinforcement Learning
In the realm of multi-agent reinforcement learning, intrinsic motivations have emerged as a pivotal tool for exploration.
Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization
Offline reinforcement learning (RL) that learns policies from offline datasets without environment interaction has received considerable attention in recent years.
Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning (MARL), the environmental stochasticity and uncertainties will increase exponentially when the number of agents increases, which puts hard pressure on how to come up with a compact latent representation from partial observation for boosting value decomposition.
SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning
In this paper, we propose a scalable value-decomposition exploration (SVDE) method, which includes a scalable training mechanism, intrinsic reward design, and explorative experience replay.
AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network
The results show that AIIR-MIX can dynamically assign each agent a real-time intrinsic reward in accordance with their actual contribution.
Curriculum Learning for Relative Overgeneralization
In multi-agent reinforcement learning (MARL), many popular methods, such as VDN and QMIX, are susceptible to a critical multi-agent pathology known as relative overgeneralization (RO), which arises when the optimal joint action's utility falls below that of a sub-optimal joint action in cooperative tasks.
Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning
e. g., an agent is a random policy while other agents are medium policies.
MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees
While achieving tremendous success in various fields, existing multi-agent reinforcement learning (MARL) with a black-box neural network architecture makes decisions in an opaque manner that hinders humans from understanding the learned knowledge and how input observations influence decisions.
Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms.