Research map / Learning theory and algorithms / Submodular and game algorithms
Regular Games -- an Automata-Based General Game Playing Language
Radosław Miernik, Marek Szykuła, Jakub Kowalski, Jakub Cieśluk, Łukasz Galas, Wojciech Pawlik
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| write the game in HRG compiled to RG instead of native RBG | RG · Connect Four | playouts per second: 914 514 -> 1 297 176 | Improved |
| write the game in HRG compiled to RG instead of native RBG | RG · Pentago (split) (lud) | playouts per second: 61 878 -> 172 626 | Improved |
| write the game in HRG compiled to RG instead of native RBG | RG · Hex (11x11) | playouts per second: 22 441 -> 23 535 | Improved |
| write the game in HRG compiled to RG instead of Ludii | RG · Gomoku (standard) | playouts per second: 19 603 -> 26 126 | Improved |
| write the game in HRG compiled to RG instead of Ludii | RG · Backgammon | playouts per second: 7 -> 2 323 | Improved |
| automatically translate RBG to RG instead of using native RBG | RG · Hex (11x11) | playouts per second: 22 441 -> 2 447 | Hurt |
| automatically translate RBG to RG instead of using native RBG | RG · Chess | playouts per second: 995 -> 531 | Hurt |
| automatically translate RBG to RG instead of using native RBG | RG · Breakthrough | playouts per second: 50 977 -> 79 175 | Improved |
| run the optimization pipeline on automata translated from RBG | RG · RBG-translated games | automaton size: 72% fewer nodes, 66% fewer edges, 21% smaller state size | Improved |
| run the optimization pipeline on HRG games | RG · HRG games | automaton size: 47% fewer nodes, 41% fewer edges | Improved |
Closest papers by meaning
- GAVEL: Generating Games via Evolution and Language Models (NeurIPS 2024 · similarity 0.88)
- Mastering Board Games by External and Internal Planning with Language Models (ICML 2025 · similarity 0.85)
- GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations (NeurIPS 2024 · similarity 0.85)
- Can Large Language Models Master Complex Card Games? (NeurIPS 2025 · similarity 0.85)
- Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract) (AAAI 2024 · similarity 0.84)
- RL-GPT: Integrating Reinforcement Learning and Code-as-policy (NeurIPS 2024 · similarity 0.84)
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.
