UnstableBaselines/Qwen3-4B-Base-GermanWhist-v0-train
Updated
•
169
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
An Async, Online, Multi-Turn, Multi-Agent RL library for training reasoning models on TextArena games.
models
10
UnstableBaselines/Qwen3-4B-Base-ColonelBlotto-v0-train
Updated
•
172
UnstableBaselines/Qwen3-4B-Base-Snake-v0-train
Updated
•
156
UnstableBaselines/Qwen3-4B-Base-LiarsDice-v0-train
Updated
•
168
UnstableBaselines/Qwen3-4B-Base-TicTacToe-v0-train
Updated
•
159
UnstableBaselines/Qwen3-4B-Base-SimpleNegotiation-v0-train
Updated
•
175
UnstableBaselines/Qwen3-4B-Base-SimpleTak-v0-train
Updated
•
169
UnstableBaselines/Qwen3-4B-Base-Chopsticks-v0-train
Updated
•
158
UnstableBaselines/Qwen3-4B-Base-Battleship-v0-train
Updated
•
200
UnstableBaselines/Qwen3-4B-Base-ConnectFour-v0-train
Updated
•
213