paper-with-me

홈 › Papers

Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning

2019-03-20 · Chris Beeler, Uladzimir Yahorau, Rory Coles, Kyle Mills, Stephen Whitelam, Isaac Tamblyn

Using a model heat engine, we show that neural network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gradient-free reinforcement learning. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally-efficient Carnot, Stirling, or Otto cycles. When given an additional irreversible process, this evolutionary scheme learns a previously unknown thermodynamic cycle. Gradient-based reinforcement learning is able to learn the Stirling cycle, whereas an evolutionary approach achieves the optimal Carnot cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.

📄 PDF Abstract BibTeX arXiv:1903.08543

Code (1)

CLEANit/heatenginegym 공식 구현

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning

2024-04-04 · Philipp Altmann, Céline Davignon, Maximilian Zorn, Fabian Ritz 외

To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their opti…

DescriptiveDiversityreinforcement-learningReinforcement Learning (RL)

Evolutionary Action Selection for Gradient-based Policy Learning

2022-01-12 · Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu 외

Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation.The evolutionary part in these hybrid me…

continuous-controlContinuous ControlDeep Reinforcement LearningEvolutionary Algorithms

Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problems

2022-01-29 · YuHeng Lei, Yao Lyu, Guojian Zhan, Tao Zhang 외

Evolutionary algorithms (EAs) have shown promise in solving sequential decision problems (SDPs) by simplifying them to static optimization problems and searching for the optimal policy parameters in a zeroth-order way. W…

continuous-controlContinuous ControlEvolutionary AlgorithmsReinforcement Learning (RL)

Neuroevolution of Recurrent Architectures on Control Tasks

2023-04-03 · Maximilien Le Clei, Pierre Bellec

Modern artificial intelligence works typically train the parameters of fixed-sized deep neural networks using gradient-based optimization techniques. Simple evolutionary algorithms have recently been shown to also be cap…

Evolutionary AlgorithmsOpenAI Gymreinforcement-learningReinforcement Learning

Guiding Evolutionary Strategies by Differentiable Robot Simulators

2021-10-01 · Vladislav Kurenkov, Bulat Maksudov

In recent years, Evolutionary Strategies were actively explored in robotic tasks for policy search as they provide a simpler alternative to reinforcement learning algorithms. However, this class of algorithms is often cl…

reinforcement-learningReinforcement Learning (RL)