no code implementations • 14 Sep 2021 • Eshagh Kargar, Ville Kyrki
Driving in a complex urban environment is a difficult task that requires a complex decision policy.
1 code implementation • 2 Sep 2021 • Eshagh Kargar, Ville Kyrki
We propose two novel ways of integrating information across agents and time in MACRPO: First, we use a recurrent layer in critic's network architecture and propose a new framework to use a meta-trajectory to train the recurrent layer.
no code implementations • 26 Mar 2021 • Eshagh Kargar, Ville Kyrki
To do this, we train an encoder-decoder deep neural network to predict multiple application-relevant factors such as the trajectories of other agents and the ego car.
no code implementations • 2 Mar 2020 • Eshagh Kargar, Ville Kyrki
Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy.
Robotics