Research map / Learning theory and algorithms / Sample complexity
Ensemble Bootstrapping for Q-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 |
|---|---|---|---|
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI Asterix | score: 5718.1 -> 22152.5 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI Breakout | score: 333.4 -> 406.3 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI CrazyClimber | score: 111765.4 -> 127967.5 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI DoubleDunk | score: -15.8 -> -10.1 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI Gopher | score: 6940.5 -> 21940.0 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI Pong | score: 19.9 -> 21.0 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI PrivateEye | score: 100.0 -> 100.0 | No clear effect |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI Qbert | score: 6277.1 -> 14384.4 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI RoadRunner | score: 40264.9 -> 55927.5 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI Tennis | score: -1.2 -> -1.1 | Helped |
| Use an ensemble of Q estimators and average the non-selecting estimators for the bootstrap value | Deep Q-learning · ATARI VideoPinball | score: 230534.3 -> 361205.1 | Helped |
| Increase the ensemble size (ablation) | EBQL · Meta Chain MDP | performance | Helped |
Closest papers by meaning
- Deep Double Q-learning (NeurIPS 2026 · similarity 0.87)
- ADDQ: Adaptive distributional double Q-learning (ICML 2025 · similarity 0.87)
- Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.85)
- Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities (NeurIPS 2026 · similarity 0.85)
- Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning (ICLR 2025 · similarity 0.85)
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · 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.