Keywords: Deep Reinforcement Learning, Memory, Benchmark, Proximal Policy Optimization, Gated Recurrent Unit, HELM
TL;DR: Memory Gym is a novel challenge especially to memory-based agents.
Abstract: Memory Gym is a novel benchmark for challenging Deep Reinforcement Learning agents to memorize events across long sequences, be robust to noise, and generalize. It consists of the partially observable 2D environments Mortar Mayhem, Mystery Path, and Searing Spotlights. These environments are believed to be unsolvable by memory-less agents because they feature strong dependencies on memory and frequent agent-memory interactions. Several commonly used related environments do not share those qualities. Empirical results based on Proximal Policy Optimization (PPO) and Gated Recurrent Unit (GRU) underline the strong memory dependency of the contributed environments. The hardness of these environments can be smoothly scaled, while different levels of difficulty (some of them unsolved yet) emerge for Mortar Mayhem and Mystery Path. Surprisingly, Searing Spotlights poses a tremendous challenge to GRU-PPO, which remains an open puzzle. Even though the randomly moving spotlights reveal parts of the environment's ground truth, environmental ablations hint that these pose a severe perturbation to agents that leverage recurrent model architectures as their memory.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)