To be released¶
Date: Very Soon¶
Solve the issue about avail_actions;
Version: 1.1.1¶
Date: 12 May, 2024¶
Improve some algorithms, such as SAC, MASAC, DDPG, and TD3, etc.
Add multi-robot warehouse (RWARE) environment.
n_size -> buffer_size;
The saving and loading of observation status;
Unify the names of attributes for both single-agent and multi-agent DRL.
Version: 1.1.0¶
Date: 01 May, 2024¶
Support MetaDrive environment, and provide examples;
Refine the configuration settings for the gym-pybullet-drones environment;
Fix some issues about models saving;
Revise the model loading method;
Implement a configuration option for selecting different activation function of the output layer of actors for continuous control;
Update the corresponding examples to adapt the above changes;
Fix some other bugs.
Version: 1.0.11¶
Date: 11 April, 2024¶
Support and finish test for gym-pybullet-drones environments;
Fix some issues for installation of xuance. Now it is more easy to install and use;
Improve the compatibility for MacOS with Apple’s M chips;
Fix some other bugs.
Version: 1.0.8¶
Date: 3 Jan, 2024¶
Added MiniGrid environment with PPO implementations;
Added gym-pybullet-drones UAV environment with PPO implementation;
Fixed the issue of failed parameter reading for multi-agent reinforcement learning with adversarial tasks;
Fixed several bugs under the TensorFlow and MindSpore frameworks.