Research map / Reinforcement learning / Visual and representation RL
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
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 learned embedding features instead of observation features to train the diversity objective (ablation) | DOMiNO · walker.stand | diversity measured in observation features: 1.21 ± 0.05 -> 1.01 ± 0.05 | No clear effect |
| Use learned embedding features instead of observation features to train the diversity objective (ablation) | DOMiNO · walker.stand | diversity measured in embedding features: 2.14 ± 0.09 -> 2.35 ± 0.09 | No clear effect |
| Select a policy from a diverse set using 10 test trajectories, rather than relying on a single extrinsic-reward policy | DOMiNO · Control Suite held-out environment perturbations | mean episode return relative to the single-policy baseline: 1.5-2.0 | Helped |
Closest papers by meaning
- DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization (AAAI 2024 · similarity 0.91)
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.89)
- Learning Diverse Risk Preferences in Population-Based Self-Play (AAAI 2024 · similarity 0.88)
- Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning (ICLR 2024 · similarity 0.87)
- SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning (ICML 2026 · similarity 0.87)
- Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story (ICML 2025 · similarity 0.87)
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.