Research map / Learning theory and algorithms / Submodular and game algorithms
Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games Using Convolutional Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use CNN with 3x3 filters instead of 5x5 (ablation) | Poker-CNN · Video poker | average return: $0.967 -> $0.977 | Helped |
| use CNN instead of fully connected network (ablation) | Poker-CNN · Video poker | average return: $0.960 -> $0.967 | Helped |
| use CNN instead of fully connected network (ablation) | Poker-CNN · Video poker big errors | count of errors < $1.0: 83 -> 49 | Helped |
| use CNN instead of fully connected network (ablation) | Poker-CNN · 2-7 triple draw | earnings per hand: +$66.2 | Helped |
| add iterative self-play refinement (20 epochs) to initial heuristic-trained model (ablation) | Poker-CNN · 2-7 triple draw vs CNN-1 | earnings per hand: +$73.3 | Helped |
| train from heuristic-player data then self-play (ablation) | Poker-CNN · Texas Hold'em vs heuristic player | earnings per hand: -$29.3 (heuristic loses) | Helped |
| play against previous three model versions in self-play (ablation) | Poker-CNN · Texas Hold'em / triple draw | training stability | Helped |
Closest papers by meaning
- PokerBench: Training Large Language Models to Become Professional Poker Players (AAAI 2025 · similarity 0.88)
- AlphaHoldem: High-Performance Artificial Intelligence for Heads-Up No-Limit Poker via End-to-End Reinforcement Learning (AAAI 2022 · similarity 0.87)
- Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract) (AAAI 2024 · similarity 0.87)
- Learning Not to Regret (AAAI 2024 · similarity 0.87)
- Enhancing Chess Reinforcement Learning with Graph Representation (NeurIPS 2024 · similarity 0.86)
- Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.