Research map / Reinforcement learning / Visual and representation RL
Automatic Curriculum Graph Generation for Reinforcement Learning Agents
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 |
|---|---|---|---|
| learn through generated curriculum graph instead of target task from scratch | Q-learning/SARSA agents · Block Dude | game steps to convergence: 17,750 -> 13,500 | Helped |
| use the full generated curriculum instead of subsets of 3 or 4 tasks (ablation) | generated curriculum · Gridworld 10x10 | convergence speed | Helped |
| generated curriculum instead of handcrafted expert curricula | Q-learning with linear function approximation · Ms. Pac-Man | expected score | Mixed |
Closest papers by meaning
- Automated curriculum generation through setter-solver interactions (ICLR 2020 · similarity 0.92)
- PORTAL: Automatic Curricula Generation for Multiagent Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Active Curriculum Refinement for Reinforcement Learning (ICML 2026 · similarity 0.89)
- Learning Progress Driven Multi-Agent Curriculum (ICML 2025 · similarity 0.87)
- Diffusion-based Curriculum Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Implicit Curriculum in Procgen Made Explicit (NeurIPS 2024 · 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.