• Corpus ID: 199442398

Deep Reinforcement Learning in System Optimization

  title={Deep Reinforcement Learning in System Optimization},
  author={Ameer Haj-Ali and Nesreen Ahmed and Theodore L. Willke and Joseph Gonzalez and Krste Asanovi{\'c} and Ion Stoica},
The recent advancements in deep reinforcement learning have opened new horizons and opportunities to tackle various problems in system optimization. Such problems are generally tailored to delayed, aggregated, and sequential rewards, which is an inherent behavior in the reinforcement learning setting, where an agent collects rewards while exploring and exploiting the environment to maximize the long term reward. However, in some cases, it is not clear why deep reinforcement learning is a good… 
World-Models for Bitrate Streaming
This project explores using supervised learning to construct a world-model, or a learned simulator, from recorded interactions, and highlights the potential for world-models to quickly learn simulators, and to be used for generating optimal policies.
Verifying learning-augmented systems
WhiRL is presented, a platform for verifying DRL policies for systems, which combines recent advances in the verification of deep neural networks with scalable model checking techniques, and is capable of guaranteeing that natural requirements from recently introduced learning-augmented systems are satisfied, and of exposing specific scenarios in which other basic requirements are not.
Reinforcement Learning for Caching with Space-Time Popularity Dynamics
This chapter presents a versatile reinforcement learning based approach for near-optimal caching policy design, in both single-node and network caching settings under dynamic space-time popularities, and demonstrates the merits of the presented approach relative to several standard caching policies.
Context-aware Distribution of Fog Applications Using Deep Reinforcement Learning
A context-aware mechanism for distributing applications across the Cloud and the Fog that relies on deep Q-networks to generate a distribution plan without prior knowledge of the available resources on the Fog node, the network condition and the application is proposed.


Reinforcement learning for robots using neural networks
This dissertation concludes that it is possible to build artificial agents than can acquire complex control policies effectively by reinforcement learning and enable its applications to complex robot-learning problems.
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
This paper proposes soft actor-critic, an off-policy actor-Critic deep RL algorithm based on the maximum entropy reinforcement learning framework, and achieves state-of-the-art performance on a range of continuous control benchmark tasks, outperforming prior on-policy and off- policy methods.
Reinforcement learning in robotics: A survey
This article attempts to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots by highlighting both key challenges in robot reinforcement learning as well as notable successes.
Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
This paper presents a comprehensive literature review on applications of deep reinforcement learning (DRL) in communications and networking, and presents applications of DRL for traffic routing, resource sharing, and data collection.
Deep Reinforcement Learning with Double Q-Learning
This paper proposes a specific adaptation to the DQN algorithm and shows that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.
Deep Q-learning From Demonstrations
This paper presents an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstrating data and is able to automatically assess the necessary ratio of demonstrationData while learning thanks to a prioritized replay mechanism.
Is Q-learning Provably Efficient?
Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically
Reinforcement Learning: An Introduction
This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Dopamine: A Research Framework for Deep Reinforcement Learning
Dopamine is an open-source, TensorFlow-based, and compact and reliable implementations of some state-of-the-art deep RL agents that complement this offering with a taxonomy of the different research objectives in deep RL research.
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
This paper proposes a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting and demonstrates that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.