arXiv subjects

Jiale Chen

Publications and source records attributed to Jiale Chen.

75 records · Page 5Linked to original sources

arXiv2019

Development of CFETR scenarios with self-consistent core-pedestal coupled simulations

This paper develops two non-inductive steady state scenarios for larger size configuration of China Fusion Engineering Test Reactor (CFETR) with integrated modeling simulations. A self-consistent core-pedestal coupled workflow for CFETR is developed under integrated modeling framework OMFIT, which allows more accurate evaluation of CFETR performance. The workflow integrates equilibrium code EFIT, transport codes ONETWO and TGYRO, and pedestal code EPED. A fully non-inductive baseline phase I scenario is developed with the workflow, which satisfies the minimum goal of Fusion Nuclear Science Facility. Compared with previous work, which proves the larger size and higher toroidal field CFETR configuration than has the advantages of reducing heating and current drive requirements, lowering divertor and wall power loads, allowing higher bootstrap current fraction and better confinement. A fully non-inductive high-performance phase II scenario is developed, which explores the alpha-particle dominated self-heating regime. Phase II scenario achieves the target of fusion power Pfus>1GW and fusion gain Qfus>20, and it largely reduces auxiliary heating and current drive power. Moreover, the large neutron production of phase II increases the energy generation power and tritium breeding rate.

physics.plasm-ph↗

arXiv2019

Asynchronous Episodic Deep Deterministic Policy Gradient: Towards Continuous Control in Computationally Complex Environments

Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in computationally complex environments. In this paper, we propose Asynchronous Episodic DDPG (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training stability diminish as the degree of parallelism increases. We consider this problem from the perspectives of both data generation and data utilization. In detail, we re-design experience replay by introducing the idea of episodic control so that the agent can latch on good trajectories rapidly. In addition, we also inject a new type of noise in action space to enrich the exploration behaviors. Experiments demonstrate that our AE-DDPG achieves higher rewards and requires less time consuming than most popular RL algorithms in Learning to Run task which has a computationally complex environment. Not limited to the control tasks in computationally complex environments, AE-DDPG also achieves higher rewards and 2- to 4-fold improvement in sample efficiency on average compared to other variants of DDPG in MuJoCo environments. Furthermore, we verify the effectiveness of each proposed technique component through abundant ablation study.

cs.LG↗

arXiv2018

Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments

In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement learning approaches, based on algorithms such as Deep Deterministic Policy Gradient, Proximal Policy Optimization, and Trust Region Policy Optimization. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each of the eight teams implemented different modifications of the known algorithms.

cs.LG↗