mlsanityData to 14 Oct 2026

Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening

arXiv 1611.01606 ↗First posted 5 Nov 2016cs.LG stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the training time. We evaluate the performance of our approach on the 49 games of the challenging Arcade Learning Environment, and report significant improvements in both training time and accuracy.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 1; 2021: 6; 2022: 4; 2023: 3; 2024: 3; 2025: 0; 2026: 3.

21 papers.

Sort:

By area:

  1. 2018Self-Imitation Learningcited by 138
  2. 2021Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planningcited by 43
  3. 2021Generalizable Episodic Memory for Deep Reinforcement Learningcited by 23
  4. 2021Regularized Softmax Deep Multi-Agent Q-Learningcited by 19
  5. 2022Constrained unsupervised anomaly segmentationcited by 19
  6. 2022Test-Time Adaptation with Shape Moments for Image Segmentationcited by 19
  7. 2023B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesiscited by 17
  8. 2021Model-Based Episodic Memory Induces Dynamic Hybrid Controlscited by 14
  9. 2020Self-Imitation Learning via Generalized Lower Bound Q-learningcited by 13
  10. 2023Weakly Coupled Deep Q-Networkscited by 6
  11. 2021Looking at the whole picture: constrained unsupervised anomaly segmentationcited by 4
  12. 2024Boosting Soft Q-Learning by Boundingcited by 4
9 more
  1. 2021Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methodscited by 2
  2. 2022MAN: Multi-Action Networks Learningcited by 2
  3. 2024Highway Reinforcement Learningcited by 2
  4. 2023Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularizationcited by 1
  5. 2022Knowing the Past to Predict the Future: Reinforcement Virtual Learningcited by 0
  6. 2024Efficient Offline Reinforcement Learning: First Imitate, then Improvecited by 0
  7. 2026Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalitiescited by 0
  8. 2026Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learningcited by 0
  9. 2026Lifted Bellman Linear Programming for Offline Reinforcement Learningcited by 0