-
I conducted experiments using dqn and colight methods on a 6x6 network, and the final results were as follows:
Dqn: Final Travel Time is 214.5438, mean rewards: -14.1031, queue: 0.4005, delay: 0.0308…
-
https://arxiv.org/abs/1707.01495
-
Would be great to be resolved along with #1773.
-
-
Hello is there any interest in adding the Rainbow DQN model similar to how it is in https://github.com/thu-ml/tianshou
-
Tried to run rl with new gym wrapper code and it gives out the following error
`expected dense_input to have shape (1, 10) but got array with shape (1, 2)`
this is the code `import asyncio
from…
-
-
### Describe your feature request
Would it be possible to allow gradient accumulation for DQN? Or is there an algorithmic reason why huge batches for gradient calculation aren't useful for DQN? …
-
While running sumo command with --route-files, I am getting segmentation fault.
sumo --net-file /media/arpana/New\ Volume/TC-DQN-master/Sample\ Code/nec_traffic_v11/envs/config/traffic.net.xml --ro…
-
List of things to be added:
- [x] Normalization of inputs
- [x] Output of the dqn should be a softmax?
- [x] Check sizes of the network. I would say that the first layer is too small
- [x] Would be …