Starcraft
132 papers with code • 0 benchmarks • 6 datasets
Starcraft I is a RTS game; the task is to train an agent to play the game.
( Image credit: Macro Action Selection with Deep Reinforcement Learning in StarCraft )
Benchmarks
These leaderboards are used to track progress in Starcraft
Libraries
Use these libraries to find Starcraft models and implementations
VizDoom
StarCraft II Learning Environment
Mario AI
Lani
StarData
MSC
Most implemented papers
The StarCraft Multi-Agent Challenge
oxwhirl/pymarl
•
•
In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap.
The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems.
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted.
StarCraft II: A New Challenge for Reinforcement Learning
Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain.
Relational Deep Reinforcement Learning
inoryy/reaver
•
•
We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning.
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
facebookresearch/benchmarl
•
•
Most recently developed approaches to cooperative multi-agent reinforcement learning in the \emph{centralized training with decentralized execution} setting involve estimating a centralized, joint value function.
Perceiver IO: A General Architecture for Structured Inputs & Outputs
deepmind/deepmind-research
•
•
ICLR 2022
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Counterfactual Multi-Agent Policy Gradients
COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies.
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
cts198859/deeprl_dist
•
•
ICML 2017
Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems.
QPLEX: Duplex Dueling Multi-Agent Q-Learning
This paper presents a novel MARL approach, called duPLEX dueling multi-agent Q-learning (QPLEX), which takes a duplex dueling network architecture to factorize the joint value function.
