Pipeline mind map
Standard pipeline template for a agents competition. Not yet specialised by an editor.
Data processing
- Read the environment / API spec
- Log episodes or traces
Model design
- Rule-based baseline
- LLM or search policy
Training
- Self-play or offline evaluation
- Track win rate / score
Post-processing
- Time and resource limits
- Safe fallbacks
Metric
cabt_bo3.
Public baselines
Most-voted public notebooks, refreshed daily from the Kaggle API (last 2026-10-10).
- Pokemon Challenge Ultra 900+ ▲21
- PTCG Hierarchical Policy & Bradley-Terry Modeling ▲17
- Rising Tide Fleet Agents ▲15
- pokémon notebook ▲13
- Q Learning Baseline ▲11
- PTCG Meta Snapshot: Do Pilots Beat Decks? ▲9
- PTCG AI Battle Challenge Playground ▲6
- PTCG Challenge Ultimate Sport 1000+ ▲5
- PTCG AI Battle: Hybrid Neural-Tactical Agent (V2) ▲5
- PTCG Pokemon Framework ▲4
- PTCG | Think About Moves ▲3
- PTCG AI Battle Playground: Baseline + New Cards ▲2
Discussion 0
No discussion yet. Ask the first question or post a team-up for this competition.
Sign in with PocketPlay
Sign-in opens soon. Until then the forum is read-only.
Same account as pocketplay.win (Google or username). Posting needs a Google-linked account.
Markdown: **bold**, *italic*, `code`, ``` code blocks, - lists, > quotes, [text](https://link). No HTML.