Tonghan Wang (@TonghanWang)
github

TonghanWang

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    391
  • Global Rank 71,242 (Top 3 %)
  • Followers 130
  • Following 9
  • Registered over 6 years ago
  • Most used languages
    Python
         100.0 %
  • Location πŸ‡¨πŸ‡³ China
  • Country Total Rank 10,578
  • Country Ranking
    Python
         1,714

Top repositories

1

ROMA

Codes accompanying the paper "ROMA: Multi-Agent Reinforcement Learning with Emergent Roles" (ICML 2020 https://arxiv.org/abs/2003.08039)
Python
148
star
2

NDQ

Codes accompanying the paper "Learning Nearly Decomposable Value Functions with Communication Minimization" (ICLR 2020)
Python
82
star
3

RODE

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.
Python
67
star
4

DOP

Codes accompanying the paper "DOP: Off-Policy Multi-Agent Decomposed Policy Gradients" (ICLR 2021, https://arxiv.org/abs/2007.12322)
Python
51
star
5

EITI-EDTI

Codes accompanying the paper "Influence-Based Multi-Agent Exploration" (ICLR 2020 spotlight)
Python
28
star
6

CASEC-MACO-benchmark

Codes accompanying the paper "Context-Aware Sparse Deep Coordination Graphs (https://arxiv.org/abs/2106.02886).
Python
14
star