DmsJin/sokoban_3b_grpo_50steps
Updated
DmsJin
AI & ML interests
None yet
Recent Activity
authored a paper about 2 months ago
RAGEN-2: Reasoning Collapse in Agentic RL upvoted a paper about 2 months ago
RAGEN-2: Reasoning Collapse in Agentic RL updated a model 4 months ago
DmsJin/sokoban_3b_grpo_50stepsOrganizations
None yet