# Robust Deep Reinforcement Learning Scheduling via Weight Anchoring

arXiv: https://arxiv.org/abs/2304.10176 · HTML: https://mlsanity.com/paper/2304.10176/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 12 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Deep Learning in Mobile and Wireless Networking: A Survey](https://mlsanity.com/paper/1803.04311/) (2018)
- [Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication](https://mlsanity.com/paper/1911.03264/) (2019)
- [The problem with DDPG: understanding failures in deterministic environments with sparse rewards](https://mlsanity.com/paper/1911.11679/) (2019)
- [Autonomous Braking System via Deep Reinforcement Learning](https://mlsanity.com/paper/1702.02302/) (2017)
- [Learning Resource Scheduling with High Priority Users using Deep Deterministic Policy Gradients](https://mlsanity.com/paper/2304.09488/) (2023)

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

- [A Multi-Task Approach to Robust Deep Reinforcement Learning for Resource Allocation](https://mlsanity.com/paper/2304.12660/) (2023)

## Abstract (arXiv)

Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired behavior in Neural Networks. Weight anchoring may be used to find a solution to a learning problem that is nearby the solution of another learning problem. Thereby, learning can be carried out in optimal environments without neglecting or unlearning desired behavior. We demonstrate this approach on the example of learning mixed QoS-efficient discrete resource scheduling with infrequent priority messages. Results show that this method provides performance comparable to the state of the art of augmenting a simulation environment, alongside significantly increased robustness and steerability.