Stars
Optimized primitives for collective multi-GPU communication
DingLyu / Deep-reinforcement-learning-with-pytorch
Forked from sweetice/Deep-reinforcement-learning-with-pytorchPyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
DingLyu / BenchMARL
Forked from facebookresearch/BenchMARLA collection of MARL benchmarks based on TorchRL
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
Python - 100天从新手到大师