Research map / Reinforcement learning / RL from feedback
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
Geonwoo Cho, Jaemoon Lee, Jaegyun Im, Subi Lee, Jihwan Lee, Sundong Kim
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 |
|---|---|---|---|
| add RND exploration reward (ablation) | AMPED · URLB Walker | sum of episode returns: 2383 -> 3021 | Improved |
| add RND exploration reward (ablation) | AMPED · URLB Quadruped | sum of episode returns: 2523 -> 3010 | Improved |
| add RND exploration reward (ablation) | AMPED · URLB Jaco | sum of episode returns: 586 -> 581 | No clear effect |
| add AnInfoNCE diversity term (ablation) | AMPED · URLB Walker | sum of episode returns: 2849 -> 3021 | Improved |
| add AnInfoNCE diversity term (ablation) | AMPED · URLB Quadruped | sum of episode returns: 2938 -> 3010 | Improved |
| add AnInfoNCE diversity term (ablation) | AMPED · URLB Jaco | sum of episode returns: 485 -> 581 | Improved |
| add gradient surgery (ablation) | AMPED · URLB Walker | sum of episode returns: 2890 -> 3021 | Improved |
| add gradient surgery (ablation) | AMPED · URLB Quadruped | sum of episode returns: 2731 -> 3010 | Improved |
| add gradient surgery (ablation) | AMPED · URLB Jaco | sum of episode returns: 427 -> 581 | Improved |
| add skill selector (ablation) | AMPED · URLB Walker | sum of episode returns: 3036 -> 3021 | No clear effect |
| add skill selector (ablation) | AMPED · URLB Quadruped | sum of episode returns: 2824 -> 3010 | Improved |
| add skill selector (ablation) | AMPED · URLB Jaco | sum of episode returns: 555 -> 581 | Improved |
Closest papers by meaning
- Exploration by Learning Diverse Skills through Successor State Representations (NeurIPS 2024 · similarity 0.87)
- Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity (NeurIPS 2024 · similarity 0.86)
- Efficient Skill Discovery via Regret-Aware Optimization (ICML 2025 · similarity 0.86)
- Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts (ICML 2024 · similarity 0.86)
- On Generalization Across Environments In Multi-Objective Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Skill Disentanglement in Reproducing Kernel Hilbert Space (AAAI 2025 · 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.
