ns-3 meets OpenAI Gym

Gawłowicz, Piotr; Zubow, Anatolij

doi:10.1145/3345768.3355908

Cited by 88 publications

(22 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To study the performance of a reinforcement learning agent, we need to specify the environment for the test. We will consider the frozen-lake [29] and cognitive-radio [30] environments. The reason why we choose the frozen-lake environment is two-fold.…”

Section: Testing Environmentsmentioning

confidence: 99%

“…• Observation: ns3 [30] statistics with the radio channels capacity, with a customized channel number = n. (e.g., a state of [1 0 0 0] represents for n = 4 channels and a primary user on the 1st channel.)…”

Section: B Cognitive Radiomentioning

confidence: 99%

“…In the experiments on the cognitive radio [30], the total number of channels n that can be selected by the agent at each time-step is known in advance. Since the occupied channel changes from time to time, it is necessary to include not only the channel but also the temporal information into This work is licensed under a Creative Commons Attribution 4.0 License.…”

Section: B Quantum Circuit For Cognitive Radio Networkmentioning

confidence: 99%

“…Furthermore, we generalize variational quantum circuits to standard DRL based action-value function approximation [27], [28]. Finally, we analyze the policy reward and the memory cost for performance of our variational quantum circuits (VQC) based DRL in comparison with standard RL and DRL approaches in the context of frozen-lake [29] and cognitive-radio [30] environments. The frozen lake is a simple maze environment in openAI Gym [29] and is a typical and simple example that is demonstrated in standard RL.…”

Section: Introductionmentioning

confidence: 99%

“…The frozen lake is a simple maze environment in openAI Gym [29] and is a typical and simple example that is demonstrated in standard RL. Cognitive radio is a wireless technology that enables for optimizing the use of available communication channels between users and has been studied by the standard machine learning technique [6], [30]. Under current limitations on the scale of quantum machines and the capabilities of quantum simulations, we select the frozen-lake and cognitive-radio environments for the proof-of-principle quantum machine learning study.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Variational Quantum Circuits for Deep Reinforcement Learning

et al. 2020

View full text Add to dashboard Cite

The state-of-the-art machine learning approaches are based on classical von Neumann computing architectures and have been widely used in many industrial and academic domains. With the recent development of quantum computing, researchers and tech-giants have attempted new quantum circuits for machine learning tasks. However, the existing quantum computing platforms are hard to simulate classical deep learning models or problems because of the intractability of deep quantum circuits. Thus, it is necessary to design feasible quantum algorithms for quantum machine learning for noisy intermediate scale quantum (NISQ) devices. This work explores variational quantum circuits for deep reinforcement learning. Specifically, we reshape classical deep reinforcement learning algorithms like experience replay and target network into a representation of variational quantum circuits. Moreover, we use a quantum information encoding scheme to reduce the number of model parameters compared to classical neural networks. To the best of our knowledge, this work is the first proof-of-principle demonstration of variational quantum circuits to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and target network. Besides, our variational quantum circuits can be deployed in many near-term NISQ machines.

show abstract

Section: Testing Environmentsmentioning

confidence: 99%

Section: B Cognitive Radiomentioning

confidence: 99%

Section: B Quantum Circuit For Cognitive Radio Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations