Pytorch implementation of intrinsic curiosity module with proximal policy optimization
This Repository is Reinforcece Learning Implementation related with PPO. The framework used in this Repository is Pytorch. The multi-processing method is basically built in. The agents are trained by PAAC(Parallel Advantage Actor Critic) strategy.
[1] mario_rl
[2] Proximal Policy Optimization
[2] Efficient Parallel Methods for Deep Reinforcement Learning
[3] High-Dimensional Continuous Control Using Generalized Advantage Estimation
[4] Curiosity-driven Exploration by Self-supervised Prediction
[5] Large-Scale Study of Curiosity-Driven Learning
[6] curiosity-driven-exploration-pytorch
[7] ml-agents