Search Results for "strategy"

...It employs Multi-head Latent Attention (MLA) and the DeepSeekMoE architecture to enhance computational efficiency. The model introduces an auxiliary-loss-free load balancing strategy and a multi-token prediction training objective to boost performance. Trained on 14.8 trillion diverse, high-quality tokens, DeepSeek-V3 underwent supervised fine-tuning and reinforcement learning to fully realize its capabilities. Evaluations indicate that it outperforms other open-source models and rivals leading closed-source models, achieving this with a training duration of 55 days on 2,048 Nvidia H800 GPUs, costing approximately $5.58 million.

MedicalGPT training medical GPT model with ChatGPT training pipeline, implementation of Pretraining, Supervised Finetuning, Reward Modeling and Reinforcement Learning. MedicalGPT trains large medical models, including secondary pre-training, supervised fine-tuning, reward modeling, and reinforcement learning training.

RLCard is a toolkit for reinforcement learning research on card games. It includes several popular card games and focuses on learning algorithms for imperfect information games like poker and blackjack.

Google Research Football is a reinforcement learning environment simulating soccer matches. It focuses on learning complex behaviors such as team collaboration and strategy formation in competitive settings.

DouZero is a reinforcement learning-based AI for playing DouDizhu, a popular Chinese card game. It focuses on perfecting AI strategies for competitive play using value-based deep RL techniques.

SMAC (StarCraft II Multi-Agent Challenge) is a benchmark environment for cooperative multi-agent reinforcement learning (MARL), based on real-time strategy (RTS) game scenarios in StarCraft II. It allows researchers to test algorithms where multiple units (agents) must collaborate to win battles against built-in game AI opponents. SMAC provides a controlled testbed for studying decentralized execution and centralized training paradigms in MARL.

...On common CNNs, it runs training 1.2~5x faster than the equivalent Keras code. Your training can probably gets faster if written with Tensorpack. Scalable data-parallel multi-GPU / distributed training strategy is off-the-shelf to use. Squeeze the best data loading performance of Python with tensorpack.dataflow. Symbolic programming (e.g. tf.data) does not offer the data processing flexibility needed in research. Tensorpack squeezes the most performance out of pure Python with various auto parallelization strategies. There are too many symbolic function wrappers already. ...