Reinforcement Learning

AssembleNIST: Assembly Policy Learning in MuJoCo

An open-source implementation of AlphaNIST in MuJoCo. One RL policy assembles all 20 parts of the NIST task board with 98.7% success.

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Scaling reasoning through reinforcement learning, with advances in training data, reward modeling, algorithms, and distributed infrastructure.