This is a modified implementation of DDPG (Deep Deterministic Policy Gradient) in OpenAI's Ant-v2 environment. This is my first attempt of a DRL algorithm implementation from scratch, so don't be too harsh! (Also, this is like my first proper coding project... haha...) Thus, it is mainly just for me to improve my PyTorch skills (educational value) Don't expect much maintenance then.
-JalterMain