{"url":"/dataset/popgym","name":"POPGym","full_name":"Partially Observable Process Gym","description_markdown":"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](https://github.com/openai/gym) interface. Our environments follow a few basic tenets:\r\n\r\n1. **Painless Setup** - `popgym` environments require only `gym`, `numpy`, and `mazelib` as dependencies\r\n2. **Laptop-Sized Tasks** - Most tasks can be solved in less than a day on the CPU \r\n3. **True Generalization** - All environments are heavily randomized.\r\n\r\nThe paper uses 15M environment steps for each trial.","description_withheld":null,"homepage":"https://github.com/proroklab/popgym","introduced_date":"2022-09-22","introduced_date_note":null,"introduced_by":null,"license":{"name":"MIT","url":null},"modalities":[{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"General Reinforcement Learning","url":"/task/general-reinforcement-learning","datasets_with_task":"/datasets/task/general-reinforcement-learning"},{"name":"Reinforcement Learning (RL)","url":"/task/reinforcement-learning-1","datasets_with_task":"/datasets/task/reinforcement-learning-1"},{"name":"Temporal Sequences","url":"/task/temporal-sequences","datasets_with_task":"/datasets/task/temporal-sequences"},{"name":"Partially Observable Reinforcement Learning","url":"/task/partially-observable-reinforcement-learning","datasets_with_task":"/datasets/task/partially-observable-reinforcement-learning"},{"name":"Model-based Reinforcement Learning","url":"/task/model-based-reinforcement-learning","datasets_with_task":"/datasets/task/model-based-reinforcement-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["POPGym"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}