Simple under-testing scripts concern about continuous actions of DQN agent for VREP simluating domain.
NOTE: The code is very beta version, and will not guarantee to work
Scripts implemented based on:
- Timothy P. Lillicrap et al., "Continuous control with deep reinforcement learning"
DQN code-base originated from DQN-chainer
This repo works under following conditions:
- RL-Glue Core 3.04
- RL-Glue Python codec
- Chainer 1.5.1 : https://github.com/pfnet/chainer
- VREP 3.2.3 rev4 : http://www.coppeliarobotics.com/
- Python 2.7+
- Linux Ubuntu 14.04