Dataset Groups Activity Stream Gridworld Environments and Sokoban Puzzles The dataset used in the paper is a set of gridworld environments and Sokoban puzzles. BibTex: @dataset{Fabio_Pardo_and_Vitaly_Levdik_and_Petar_Kormushev_2025, abstract = {The dataset used in the paper is a set of gridworld environments and Sokoban puzzles.}, author = {Fabio Pardo and Vitaly Levdik and Petar Kormushev}, doi = {10.57702/euaw5vbz}, institution = {No Organization}, keyword = {'Sokoban', 'goal-conditioned policy', 'gridworld', 'reinforcement learning'}, month = {jan}, publisher = {TIB}, title = {Gridworld Environments and Sokoban Puzzles}, url = {https://service.tib.eu/ldmservice/dataset/gridworld-environments-and-sokoban-puzzles}, year = {2025} }