Accelerating Q-learning through Efficient Value-Sharing across Actions

arXiv:2606.29806 · cs.LG, cs.AI · Submitted 2026-06-29 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-06-29

Updated: 2026-09-17

Comments: ICML 2026 (Spotlight); Adaptive and Learning Agents workshop 2026 (Best paper runner-up)

Code: https://github.com/prabhatnagarajan/me

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Q-learning — 55× in this paper · explained in 3 episodes
• Reinforcement Learning — 20× in this paper · explained in 4 episodes
• Adam — 14× in this paper · explained in 2 episodes
• Sample Efficiency — 6× in this paper · explained in 4 episodes
• Arcade Learning Environment — 5× in this paper
• Regularization — 5× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 4× in this paper · explained in 2 episodes
• In International Conference on Machine Learning — 4× in this paper
• AUC — 3× in this paper · explained in 2 episodes
• Action Space — 3× in this paper · explained in 1 episode
• Generalization — 3× in this paper · explained in 13 episodes
• Reinforcement Learning (RL) — 3× in this paper · explained in 25 episodes
• Implicit-Baseline Q-learning — 2× in this paper
• Loss Function — 2× in this paper · explained in 2 episodes
• Reinforcement Learning Journal — 2× in this paper
• Sample Complexity — 2× in this paper · explained in 15 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Area Under the Curve (AUC) — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Regularized Dueling Qlearning — 1× in this paper
• Reward Function — 1× in this paper · explained in 2 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes

Sources

• Deep Double Q-learning
• MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
• Gymnasium: A Standard Interface for Reinforcement Learning Environments

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks