Research map / Reinforcement learning / Visual and representation RL
Effective Diversity in Population Based 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 |
|---|---|---|---|
| add determinant-based diversity to an ensemble of TD3 policies | TD3 · Humanoid-v2 | median best reward: 5654 -> 6091 | Helped |
| add determinant-based diversity to TD3 with a population of policies | TD3 · Humanoid-v2 | median best reward: 5727 -> 6091 | Helped |
| replace the Squared Exponential kernel with alternative kernels (ablation) | DvD-ES · Point, Swimmer, Walker2d | median maximum reward: Point: -547.03; Swimmer: 354.86; Walker2d: 1925.86 | Mixed |
| fix diversity weight at lambda=0.5 instead of adapting it online (ablation) | DvD-ES · Point, Swimmer, Walker2d, and other tested tasks | reward | Hurt |
| vary the number and selection strategy of states used in the behavioral embedding (ablation) | DvD-ES · Point and Swimmer | reward | No clear effect |
| increase population size from M=3 to M=5 when the tasks have two modes (ablation) | DvD-ES · Cheetah and Ant multi-modal tasks | performance | Hurt |
Closest papers by meaning
- Diversity-Driven Exploration Strategy for Deep Reinforcement Learning (NeurIPS 2018 · similarity 0.92)
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.90)
- DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization (AAAI 2024 · similarity 0.90)
- Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story (ICML 2025 · similarity 0.89)
- Learning Diverse Risk Preferences in Population-Based Self-Play (AAAI 2024 · similarity 0.88)
- Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity (NeurIPS 2024 · similarity 0.88)
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.