search

stevenpjg / ddpg-aigym

Continuous control with deep reinforcement learning - Deep Deterministic Policy Gradient (DDPG) algorithm implemented in OpenAI Gym environments
MIT License
272 stars 74 forks source link

what the grad_inverter means? #15

Closed pringwong closed 5 years ago

pringwong commented 5 years ago

why to filter by zero, and calculate the gradients by different ways?

stevenpjg commented 5 years ago

Please refer to http://arxiv.org/abs/1511.04143 for more info.