# Directly Attention Loss Adjusted Prioritized Experience Replay

arXiv: https://arxiv.org/abs/2311.14390 · HTML: https://mlsanity.com/paper/2311.14390/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 24 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay](https://mlsanity.com/paper/2007.06049/) (2020)
- [Prioritized Sequence Experience Replay](https://mlsanity.com/paper/1905.12726/) (2019)
- [Actor Prioritized Experience Replay](https://mlsanity.com/paper/2209.00532/) (2022)
- [Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning](https://mlsanity.com/paper/2209.13220/) (2022)
- [Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment](https://mlsanity.com/paper/1905.09673/) (2019)
- [Continuous Multi-objective Zero-touch Network Slicing via Twin Delayed DDPG and OpenAI Gym](https://mlsanity.com/paper/2101.06617/) (2021)
- [Double Prioritized State Recycled Experience Replay](https://mlsanity.com/paper/2007.03961/) (2020)
- [Attention Loss Adjusted Prioritized Experience Replay](https://mlsanity.com/paper/2309.06684/) (2023)

## Built on by (most cited first, 1 of 1)

- [Self-Organizing Dual-Buffer Adaptive Clustering Experience Replay (SODACER) for Safe Reinforcement Learning in Optimal Control](https://mlsanity.com/paper/2601.06540/) (2026)

## Abstract (arXiv)

Prioritized Experience Replay (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that is originally used to estimate Q-value functions, which brings about the estimation deviation. In this article, an novel off policy reinforcement learning training framework called Directly Attention Loss Adjusted Prioritized Experience Replay (DALAP) is proposed, which can directly quantify the changed extent of the shifted distribution through Parallel Self-Attention network, so as to accurately compensate the error. In addition, a Priority-Encouragement mechanism is designed simultaneously to optimize the sample screening criterion, and further improve the training efficiency. In order to verify the effectiveness and generality of DALAP, we integrate it with the value-function based, the policy-gradient based and multi-agent reinforcement learning algorithm, respectively. The multiple groups of comparative experiments show that DALAP has the significant advantages of both improving the convergence rate and reducing the training variance.