2024
Grasp Multiple Objects With One Hand.
IEEE Robotics Autom. Lett., May, 2024

SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning.
CoRR, 2024

Natural Language Reinforcement Learning.
CoRR, 2024

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search.
CoRR, 2024

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data.
CoRR, 2024

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.
CoRR, 2024

DeepSeek-VL: Towards Real-World Vision-Language Understanding.
CoRR, 2024

DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.
CoRR, 2024

2023
TorchOpt: An Efficient Library for Differentiable Optimization.
J. Mach. Learn. Res., 2023

2022
EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
Settling the Bias and Variance of Meta-Gradient Estimation for Meta-Reinforcement Learning.
CoRR, 2021

Discovering Multi-Agent Auto-Curricula in Two-Player Zero-Sum Games.
CoRR, 2021

Neural Auto-Curricula in Two-Player Zero-Sum Games.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Learning Correlated Communication Topology in Multi-Agent Reinforcement learning.
Proceedings of the AAMAS '21: 20th International Conference on Autonomous Agents and Multiagent Systems, 2021