Papers with Code 아카이브

Real-Time Strategy Games

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 0
보존된 평가 기록: 0

Real-Time Strategy (RTS) tasks involve training an agent to play video games with continuous gameplay and high-level macro-strategic goals such as map control, economic superiority and more.

<span style="color:grey; opacity: 0.6">( Image credit: Multi-platform Version of StarCraft: Brood War in a Docker Container )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/huggingface/transformers

Perceiver IO: A General Architecture for Structured Inputs & Outputs

https://github.com/ifpen/wfcrl-benchmark

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

https://github.com/inoryy/reaver

StarCraft II: A New Challenge for Reinforcement Learning

https://github.com/isp1tze/MAProj

Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

https://github.com/jk96491/C-COMA

The StarCraft Multi-Agent Challenge

https://github.com/jk96491/SMAC

The StarCraft Multi-Agent Challenge

https://github.com/jugg1er/air

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

https://github.com/kachayev/gym-microrts-paper-sb3

Gym-$μ$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning

https://github.com/karush17/emix

Energy-based Surprise Minimization for Multi-Agent Value Factorization

https://github.com/kcorder/qmix_variants

The StarCraft Multi-Agent Challenge

https://github.com/kered9/gym-microrts

Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games

https://github.com/kfu02/jaxmarl

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

https://github.com/kinalmehta/epymarl

The StarCraft Multi-Agent Challenge

https://github.com/krasserm/perceiver-io

Perceiver IO: A General Architecture for Structured Inputs & Outputs

https://github.com/lich14/CDS

Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

https://github.com/ling-pan/res

The StarCraft Multi-Agent Challenge

https://github.com/mahi97/XQMIX

The StarCraft Multi-Agent Challenge

https://github.com/matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients

Counterfactual Multi-Agent Policy Gradients

https://github.com/mavischer/DRRL

Relational Deep Reinforcement Learning

https://github.com/morning9393/HAPPO-HATRPO

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?

https://github.com/nathangrinsztajn/Box-World

Relational Deep Reinforcement Learning

https://github.com/nathanin/pad

Relational Deep Reinforcement Learning

https://github.com/nice-hku/cl2marl-smac

Counterfactual Multi-Agent Policy Gradients

https://github.com/nicoladainese96/RelationalDeepRL

Relational Deep Reinforcement Learning

https://github.com/nicoladainese96/SC2-RL

StarCraft II: A New Challenge for Reinforcement Learning

https://github.com/nju-rl/acorm

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

https://github.com/nvlabs/long-video-gan

Towards Accurate Generative Models of Video: A New Metric & Challenges

https://github.com/opendilab/DI-engine

Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

https://github.com/opendilab/DI-engine/blob/main/ding/policy/collaq.py

Multi-Agent Collaboration via Reward Attribution Decomposition

https://github.com/opendilab/DI-engine/blob/main/ding/policy/coma.py

Counterfactual Multi-Agent Policy Gradients

https://github.com/opendilab/DI-engine/blob/main/ding/policy/qmix.py

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

https://github.com/osilab-kaist/smac_exp

The StarCraft Multi-Agent Challenge

https://github.com/osilab-kaist/smac_plus

The StarCraft Multi-Agent Challenge

https://github.com/oxwhirl/comix

FACMAC: Factored Multi-Agent Centralised Policy Gradients

https://github.com/oxwhirl/facmac

The StarCraft Multi-Agent Challenge

https://github.com/pku-marl/harl

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.