RuanJingqing's repositories
GCS_aamas337
The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》
CARE-SMAC-MA_SAC
Multi-task Multi-agent Soft Actor Critic for SMAC
Conventions-ModularPolicy
PyTorch implementation for "On the Critical Role of Conventions in Adaptive Human-AI Collaboration", ICLR 2021
Papers-of-Offline-RL
Related papers for offline reforcement learning (we mainly focus on representation and sequence modeling and conventional offline RL)
AI-Paper-Collector
Fully-automated scripts for collecting AI-related papers
attention-learn-to-route
Attention based model for learning to solve different routing problems
Bullet-Safety-Gym
An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.
CORRO
CORRO code
Deep-Reinforcement-Learning-Algorithms
This is a reconstruction of previous repository(rl-algorithms).
DGN
DGN Code
football
Check out the new game server:
GCS
The implementation of GCS
LLaVA-RLHF
Aligning LMMs with Factually Augmented RLHF
minimalRL
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
multi-agent-PPO-on-SMAC
Implementations of MAPPO and IPPO on SMAC, the multi-agent StarCraft environment.
NLPer-Interview
该仓库主要记录 NLP 算法工程师相关的面试题
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
releasing-research-code
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
shap
A game theoretic approach to explain the output of any machine learning model.
WeTS
A benchmark for the task of translation suggestion