DirectFuturePrediction
DirectFuturePrediction copied to clipboard
Code for the paper "Learning to Act by Predicting the Future", Alexey Dosovitskiy and Vladlen Koltun, ICLR 2017
It seems like there is a mistake in the target maker. https://github.com/isl-org/DirectFuturePrediction/blob/b4757769f167f1bd7fb1ece5fdc6d874409c68a9/DFP/future_target_maker.py#L69 I guess we should substract the mean of the measurements in stead of the value of the measurement...
https://github.com/IntelVCL/DirectFuturePrediction/blob/b4757769f167f1bd7fb1ece5fdc6d874409c68a9/DFP/future_predictor_agent_advantage.py#L86 Maybe this is just me, but I find this section as described in the paper highly confusing. What exactly is **g**? Is it the objective coefficients, the temporal coefficients...
Hi, I installed all the dependent modules as required, including VizDoom, and import vizdoom works fine under test. To reproduce your experiments, the VizDoom path variable should be changed. However,...
When I read the paper, they say that it works at discrete action space. Is it also possible at continuous action space???
Hi, why the experiences contain nan?