paper-with-me

홈 › Papers

A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning

2023-03-09 · Juan Marcelo Parra-Ullauri, Chen Zhen, Antonio García-Domínguez, Nelly Bencomo, Changgang Zheng, Juan Boubeta-Puig, Guadalupe Ortiz, Shufan Yang

A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem. Hyperparameter tuning often requires manual or automated searches to find optimal values. Nonetheless, a noticeable limitation is the high cost of algorithm evaluation for complex models, making the tuning process computationally expensive and time-consuming. In this paper, we propose a framework based on integrating complex event processing and temporal models, to alleviate these trade-offs. Through this combination, it is possible to gain insights about a running RL system efficiently and unobtrusively based on data stream monitoring and to create abstract representations that allow reasoning about the historical behaviour of the RL system. The obtained knowledge is exploited to provide feedback to the RL system for optimising its hyperparameters while making effective use of parallel resources. We introduce a novel history-aware epsilon-greedy logic for hyperparameter optimisation that instead of using static hyperparameters that are kept fixed for the whole training, adjusts the hyperparameters at runtime based on the analysis of the agent's performance over time windows in a single agent's lifetime. We tested the proposed approach in a 5G mobile communications case study that uses DQN, a variant of RL, for its decision-making. Our experiments demonstrated the effects of hyperparameter tuning using history on training stability and reward values. The encouraging results show that the proposed history-aware framework significantly improved performance compared to traditional hyperparameter tuning approaches.

📄 PDF Abstract BibTeX arXiv:2303.05186

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

Combining Automated Optimisation of Hyperparameters and Reward Shape

2024-06-26 · Julian Dierkes, Emma Cramer, Holger H. Hoos, Sebastian Trimpe

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and perform…

Deep Reinforcement LearningReinforcement Learning (RL)

Bayes-Adaptive Deep Model-Based Policy Optimisation

2020-10-29 · Tai Hoang, Ngo Anh Vien

We introduce a Bayesian (deep) model-based reinforcement learning method (RoMBRL) that can capture model uncertainty to achieve sample-efficient policy optimisation. We propose to formulate the model-based policy optimis…

modelModel-based Reinforcement Learning

Cost-aware Multi-objective Bayesian optimisation

2019-09-09 · Majid Abdolshah, Alistair Shilton, Santu Rana, Sunil Gupta 외

The notion of expense in Bayesian optimisation generally refers to the uniformly expensive cost of function evaluations over the whole search space. However, in some scenarios, the cost of evaluation for black-box object…

Bayesian Optimisation

Maximum a Posteriori Policy Optimisation

2018-06-14 · ICLR 2018 1 · Abbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa, Remi Munos 외

We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly …

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+2

Population Based Training of Neural Networks

2017-11-27 · Max Jaderberg, Valentin Dalibard, Simon Osindero, Wojciech M. Czarnecki 외

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisa…

Deep Reinforcement LearningMachine TranslationModel SelectionReinforcement Learning