Research map / Reinforcement learning / Visual and representation RL
Programmatic Modeling and Generation of Real-Time Strategic Soccer Environments for Reinforcement Learning
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 |
|---|---|---|---|
| Fine-tune the GRF checkpoint with PPO on a mirrored 11v11 scenario | GRF checkpoint · 11v11 failure scenario | average goal difference: 0.1 -> 0.67 | Helped |
| Train on wider initial-state distributions | PPO agents in defense scenarios · Defense scenarios, train versus test | average goal difference | Helped |
| Use demonstration data from probabilistic SCENIC policies for behavior cloning, then PPO fine-tuning | PPO agents · Five difficult scenarios | training performance | Mixed |
| Train PPO on the EASY CROSSING scenario | PPO · EASY CROSSING | average goal difference | Helped |
| Train PPO on the HARD CROSSING scenario | PPO · HARD CROSSING | average goal difference | Hurt |
| Evaluate on scenarios with changed initial-state distributions | PPO agents trained on offense and academy scenarios · Offense and selected GRF academy scenarios, test | average goal difference | Hurt |
| Evaluate on scenarios with changed initial-state distributions | PPO agents trained on defense scenarios · Defense scenarios, test | average goal difference | No clear effect |
Closest papers by meaning
- The CoachAI Badminton Environment: Bridging the Gap between a Reinforcement Learning Environment and Real-World Badminton Games (AAAI 2024 · similarity 0.88)
- Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity (NeurIPS 2024 · similarity 0.87)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.86)
- The CoachAI Badminton Environment: A Novel Reinforcement Learning Environment with Realistic Opponents (Student Abstract) (AAAI 2024 · similarity 0.86)
- Learning Interactive Real-World Simulators (ICLR 2024 · similarity 0.85)
- Forecasting in Offline Reinforcement Learning for Non-stationary Environments (NeurIPS 2025 · similarity 0.85)
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.