vgc
Datasets
All datasets matching “vgc”vgc-battle-logsDataset from the paper VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pokémon.
Code: vgc-bench
Older Scarlet/Violet (Regs A through J) logs have been archived to vgc-battle-logs-sv.
Contains data for 4 Gen 9 Pokémon VGC Champions formats (Regs M-A and M-B), all filtered for Open Team Sheets (OTS). See:
scrape_logs.py for the code that scraped these 88,905 logs from the Pokémon Showdown replay database
logs2trajs.py for the code that reads the logs from player 1 and 2's… See the full description on the dataset page: https://huggingface.co/datasets/cameronangliss/vgc-battle-logs.VGCP_robosuite
VGCP: learning Inverse Dynamics Model using Inverse Reinforcement Learning
Preparation
1. Encoder for reward computation: The encoder is pretrained using TCC, and each is for one task. Download pretrain_runs.zip
2. Datasets for conditioning goals: The goals in observation are from a randomly sampled sequence in demonstrations. They are psuedo-goals. Download and put datasets under VGCP.
3. Finally, prepare video generative… See the full description on the dataset page: https://huggingface.co/datasets/Renton-Ren/VGCP_robosuite.vgc-battle-logs-svDataset from the paper VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pokémon.
Code: vgc-bench
This is the archive of older Scarlet/Violet (Regs A through J) logs. For the current Champions-format logs, see vgc-battle-logs.
Contains data for 18 Gen 9 Pokémon VGC Scarlet/Violet formats (Regs A through J), all filtered for Open Team Sheets (OTS). See:
scrape_logs.py for the code that scraped these 936,352 logs from the Pokémon Showdown replay database
logs2trajs.py for the… See the full description on the dataset page: https://huggingface.co/datasets/cameronangliss/vgc-battle-logs-sv.vgc-battle-logsDataset from the paper VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pokémon.
Code: vgc-bench
Contains data for 18 Gen 9 Pokémon VGC formats, all filtered for Open Team Sheets (OTS). See:
scrape_logs.py for the code that scraped these 906,870 logs from the Pokémon Showdown replay database
logs2trajs.py for the code that reads the logs from player 1 and 2's perspective, yielding 1,813,688 trajectories (99.997% successful log read rate), or 16,832,842… See the full description on the dataset page: https://huggingface.co/datasets/life1904/vgc-battle-logs.vg-captions-graphs-processed-image-graphsvg_coco_overlap_for_graphormer_processed_amr_graphs