The rule of collision penalty about agile_flight HOT 7 OPEN

I didn't tune the reward. I am not surprised that the result is not good.

Some general suggestions are

• tune the reward, check the learning curve not only for the total reward but also for each individual reward. Each individual reward component is logged. you can visualize the learning curve by cd ./saved and tensorboard --logdir=./
• use different policy representations. Currently, the policy is represented via a multilayer perception, this is not a good representation for dynamic environments. Consider using a memory-based network, such as RNN/LSTM/GRU/TCN.

from agile_flight.

the relative dist is a measurement of the euclidean distance between the drone center and the obstacle.

OK. Then, you have to check https://github.com/uzh-rpg/flightmare/blob/092ff357139b2e98fc92bcdee50f38f85b55246d/flightlib/src/envs/vision_env/vision_env.cpp#L296-L300 grammerly. I mean the usage of ? : should be condition ? case1 : case2

from agile_flight.

thanks a lot @tongtybj

from agile_flight.

hi,

the relative dist is a measurement of the euclidean distance between the drone center and the obstacle.

If the actual relative dist is larger than the section range, relative dist will be clipped as the maximum detection range. otherwise, it is the same as the actual dist.

from agile_flight.

ohhhhhhhhhhh,
you are absolutely right. sorry.

from agile_flight.

@yun-long

You are welcome.

Actually, I also trained with the true std::exp(-1.0 * relative_dist) model, but got worse result. So I wondered that you wrote in this way intentioanlly.

from agile_flight.

Thanks a lot for your important advice!

from agile_flight.