Popular repositories Loading

1. kuairand-offline-rl kuairand-offline-rl Public

   Offline contextual-bandit recommendation on KuaiRand-Pure: BC, CPL, one-step CQL, IPS/SNIPS/DR, chronological evaluation and conservative promotion gates.

   Python 1

2. agentic-rl-lab agentic-rl-lab Public

   Single-GPU agentic RL: verifiable reward, GRPO diagnostics, offline task sets, VRAM pre-flight

   Python 1

3. machine-learning machine-learning Public

   Python

4. machine-learning1 machine-learning1 Public

5. lenet lenet Public

   Python

6. alexnet alexnet Public

   Python