POPGym is designed to benchmark memory in deep reinforcement learning. It contains a set of environments and a collection of memory model baselines. The environments are all Partially Observable Markov Decision Process (POMDP) environments following the Openai Gym interface. Our environments follow a few basic tenets:
popgymenvironments require only
The paper uses 15M environment steps for each trial.
|Trend||Task||Dataset Variant||Best Model||Paper||Code|
Gated Recurrent Unit