We lifted 13 functions out of this paper's own repositories and ran 11 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| smearle/control-pcgrl | canonical | 2 of 2 |
| smearle/gym-pcgrl | pwc_unofficial | 9 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| gauss | Ran | smearle/gym-pcgrl/control_pcgrl/evo/models.py code served (permissive licence) · get_code("7e891b936316c34e") |
| get_action | Ran | smearle/gym-pcgrl/control_pcgrl/wrappers.py code served (permissive licence) · get_code("493c58a0c3e0d196") |
| get_coord_grid | Ran | smearle/gym-pcgrl/control_pcgrl/evo/models.py code served (permissive licence) · get_code("22c00a083fdac639") |
| get_floor_dist | Ran | smearle/gym-pcgrl/control_pcgrl/envs/helper.py code served (permissive licence) · get_code("1a209a0529574115") |
| get_floor_dist | Ran | smearle/gym-pcgrl/control_pcgrl/envs/helper_3D.py code served (permissive licence) · get_code("0d016df5592dba74") |
| get_stats | Ran | smearle/control-pcgrl/control_pcgrl/evo/evolve.py code served (permissive licence) · get_code("405a9f1e9dd6a316") |
| get_tile_locations | Ran | smearle/gym-pcgrl/control_pcgrl/envs/helper.py code served (permissive licence) · get_code("538a6377cf71941d") |
| get_tile_locations | Ran | smearle/gym-pcgrl/control_pcgrl/envs/helper_3D.py code served (permissive licence) · get_code("fa862d703efa2f8d") |
| get_type_grouping | Ran | smearle/gym-pcgrl/control_pcgrl/envs/helper.py code served (permissive licence) · get_code("1f551c6ddc6c9656") |
| get_type_grouping | Ran | smearle/gym-pcgrl/control_pcgrl/envs/helper_3D.py code served (permissive licence) · get_code("675f95579f098b3f") |
| tran_action | Ran | smearle/control-pcgrl/control_pcgrl/evo/evolve.py code served (permissive licence) · get_code("2fd33ffbc4e17e54") |
| disable_passive_env_checker | Not yet run | smearle/gym-pcgrl/control_pcgrl/wrappers.py code served (permissive licence) · get_code("2510fc4c8f91869b") |
| train_reward_model | Not yet run | smearle/gym-pcgrl/control_pcgrl/reward_model_wrappers.py code served (permissive licence) · get_code("21c67716d20862c2") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels. While NCAs have so far only been trained via supervised learning, we present a quality diversity (QD) approach to generating a collection of NCA level generators. By framing the problem as a QD problem, our approach can train diverse level generators, whose output levels vary based on aesthetic or functional criteria. To efficiently generate NCAs, we train generators via Covariance Matrix Adaptation MAP-Elites (CMA-ME), a quality diversity algorithm which specializes in continuous search spaces. We apply our new method to generate level generators for several 2D tile-based games: a maze game, Sokoban, and Zelda. Our results show that CMA-ME can generate small NCAs that are diverse yet capable, often satisfying complex solvability criteria for deterministic agents. We compare against a Compositional Pattern-Producing Network (CPPN) baseline trained to produce diverse collections of generators and show that the NCA representation yields a better exploration of level-space.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.05489")
get_code_for_paper("2109.05489")
have("2109.05489")
Connect an agent — have() is free.