(Work in progress)
Custom implementation of Proximal Policy Optimization (PPO) for continuous action space based on example code from Flax. Intended to support OpenAI Gym type environments or custom environments that have the same implementation.
(Work in progress)
Custom implementation of Proximal Policy Optimization (PPO) for continuous action space based on example code from Flax. Intended to support OpenAI Gym type environments or custom environments that have the same implementation.