DI-engine
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
- 3.6k
- Python
- Apache-2.0
- 12 mo ago
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)
An artificial intelligence platform for the StarCraft II with large-scale distributed training and grand-master agents.
π Threes! AI: deck-aware expectimax, N-tuple TD learning, and AlphaZero
The exact codes used by the team "liveinparis" at the kaggle football competition ranked 6th/1141
Mastering complex card games like GuanDan (ζΌθ) and DouDiZhu (ζε°δΈ») using self-play RL and causal sequence modeling with zero domain knowledge
Implementation of Self-Play Pretraining with Zero Data
Implementation of Play2Perfect, from Tyler Ga Wei Lum et al. of Stanford, but with a Self Play element
High-performance C++17 DouDizhu reinforcement learning system with Perfect Information Distillation & PPO (LibTorch)
An asynchronous implementation of AlphaZero, a self-play reinforcement learning algorithm.
One library for the frontier LLM training stack β pre-training, CPT/DAPT, SFT, DPO/IPO/KTO/ORPO/SimPO/CPO, RLHF, RLVR+GRPO, agentic RL, distillation & self-play, LoRA/QLoRA β behind one config-driven, registry-based API. import trainall is torch-free.
A polygraph for self-improving AI Β· OpenEnv 2026
Runs in the browser on Hugging Face
Train your reinforcement learning agent with self-play for the board game Abalone and play against it
Abalone player trained by reinforcement learning and neural networks, from my 1999 diploma thesis at TU Wien
Hands-on, runnable demos of SPICED (self-play + a pinch of human data, arxiv 2606.19370) at tiny scale on a Mac M5: demo-regularized self-play, the RLHF KL knob, and LoRA on a real LLM.
Mega Lucario ex heuristic agent for the PokΓ©mon TCG AI Battle Challenge, with replay diagnostics, self-play evaluation, and experimental policy/value MCTS research.