Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)
BSD-3-CLAUSE License
Published by Emerald01 11 months ago
Extend to easily support single agent framework. We start to add gym.classic_control as examples. Cartpole, Mountain Car and Acrobot have been included and they can run up to 100K concurrent replicates.
Published by Emerald01 about 1 year ago
Introduce the random reset from the pre-defined reset pool. Users are able to provide reset data pool for the corresponding data array(i.e., reset_target). During reset, the target data array will randomly pick up the reset data from the reset pool for each individual environment replica independently.
Published by Emerald01 over 1 year ago
Published by Emerald01 over 1 year ago
Release 2.3 (2022-03-22)
Release 2.2 (2022-12-20)
Release 2.1 (2022-10-26)
Published by Emerald01 about 2 years ago
Published by Emerald01 about 2 years ago
Using the extreme parallelization capability of GPUs, WarpDrive enables orders-of-magnitude faster RL compared to CPU simulation + GPU model implementations.