xxyQwQ/train-ppo-sciworld-text-qwen2.5-7b
8B • Updated • 15
Xiangyuan Xue
xxyQwQ
AI & ML interests
LLM-Based Agents, Multi-Agent Systems, Reinforcement Learning
Recent Activity
authored a paper about 10 hours ago
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction updated a collection 20 days ago
StraTA MiscellaneousOrganizations
xxyQwQ/train-grpo-sciworld-text-qwen2.5-7b
8B • Updated • 16
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-ultimate-version
3B • Updated • 10
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-diverse-version
3B • Updated • 16
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-judgment-version
3B • Updated • 19
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-vanilla-version
3B • Updated • 19
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-diverse-version
3B • Updated • 17
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-judgment-version
3B • Updated • 17
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-ultimate-version
3B • Updated • 16
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-vanilla-version
3B • Updated • 18
xxyQwQ/train-ppo-webshop-text-qwen2.5-7b
8B • Updated • 18
xxyQwQ/train-ppo-alfworld-text-qwen2.5-7b
8B • Updated • 17
xxyQwQ/train-grpo-webshop-text-qwen2.5-7b
8B • Updated • 19
xxyQwQ/train-grpo-alfworld-text-qwen2.5-7b
8B • Updated • 16
xxyQwQ/train-strata-sciworld-text-qwen2.5-7b
8B • Updated • 4
xxyQwQ/train-strata-webshop-text-qwen2.5-7b
8B • Updated • 1
xxyQwQ/train-strata-alfworld-text-qwen2.5-7b
8B • Updated • 1