Rainbow: Combining Improvements in Deep Reinforcement Learning
Combining improvements in deep reinforcement learning. Results and pretrained models can be found in the releases. Data-efficient Rainbow can be run using several options (note that the "unbounded" memory is implemented here in practice by manually setting the memory capacity to be the same as the maximum number of timesteps).
This project contains the files required to run the Cross-Entropy Relational Reinforcement Learning Agent (CERRLA) algorithm. Note that a copy of the JESS rules engine will also be required.