Reward penalties on augmented states for solving richly constrained RL effectively

Reward penalties on augmented states for solving richly constrained RL effectively

Constrained Reinforcement Learning employs trajectory-based cost constraints (such as expected cost, Value at Risk, or Conditional VaR cost) to compute safe policies. The challenge lies in handling these constraints effectively while optimizing expected reward. Existing methods convert such trajecto...

Saved in:

書目詳細資料
Main Authors:	HAO, Jiang, MAI, Tien, VARAKANTHAN, Pradeep, HOANG, Minh Huy
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2024
主題:	Safe reinforcement learning Reward penalties Constraint optimization Reinforcement learning Markov models (MDPs POMDPs) Stochastic optimization Artificial Intelligence and Robotics
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/9685 https://ink.library.smu.edu.sg/context/sis_research/article/10685/viewcontent/29962_Article_Text_34016_1_2_20240324.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Singapore Management University
語言:	English

相似書籍

Financial portfolio optimization: an autoregressive deep reinforcement learning algorithm with learned intrinsic rewards
由: Lim, Magdalene Hui Qi
出版: (2024)

SINGLE TRAJECTORY CONVERGENCE IN REINFORCEMENT LEARNING PROBLEMS WITH VECTORIAL REWARDS
由: EWE ZI YI
出版: (2021)

A STUDY OF MARKOV DECISIONS PROCESSES IN FINITE SPACES AND APPLICATION ON FISHING QUOTAS
由: CECILE MONIQUE HELENE DECKER
出版: (2023)

Imitate the good and avoid the bad: An incremental approach to safe reinforcement learning
由: HOANG, Minh Huy, et al.
出版: (2024)

Safety through feedback in constrained RL
由: CHIRRA, Shashank Reddy, et al.
出版: (2024)

Solving Uncertain MDPs with Objectives that are Separable over Instantiations of Model Uncertainty
由: ADULYASAK, Yossiri, et al.
出版: (2015)

Personalized robotic control via constrained multi-objective reinforcement learning
由: He, Xiangkun, et al.
出版: (2024)

Constrained multiagent reinforcement learning for large agent population
由: LING, Jiajing, et al.
出版: (2022)

Coordination guided reinforcement learning
由: Lau, Q.P., et al.
出版: (2014)

Constrained reinforcement learning in hard exploration problems
由: PATHMANATHAN, Pankayaraj, et al.
出版: (2023)

Resting-state EEG theta activity and risk learning: Sensitivity to reward or punishment?
由: Massar, S.A.A., et al.
出版: (2016)

ENERGY EFFICIENT PATH PLANNING WITH REINFORCEMENT LEARNING
由: JEROME ALEXANDRE ROCHE
出版: (2023)

A differential dynamic programming framework for inverse reinforcement learning
由: Cao, Kun, et al.
出版: (2025)

SEAPoT-RL: Selective exploration algorithm for policy transfer in RL
由: NARAYAN, Akshay, et al.
出版: (2017)

Constrained multiagent reinforcement learning for large agent population
由: LING, Jiajing, et al.
出版: (2023)

Reinforcement learning for collective multi-agent decision making
由: NGUYEN, Duc Thien
出版: (2018)

GFANC-RL: reinforcement learning-based generative fixed-filter active noise control
由: Luo, Zhengding, et al.
出版: (2024)

SCALES: From Fairness Principles to Constrained Decision-Making
由: Balakrishnan, Sreejith, et al.
出版: (2022)

TOWARDS HUMAN-CENTRIC AI: INVERSE REINFORCEMENT LEARNING MEETS ALGORITHMIC FAIRNESS
由: SREEJITH BALAKRISHNAN
出版: (2023)

Difference of convex functions programming for policy optimization in reinforcement learning
由: KUMAR, Akshat
出版: (2024)

SAFETY AND RELIABILITY IN BAYESIAN OPTIMIZATION: ALGORITHMS AND REGRET GUARANTEES
由: ARPAN LOSALKA
出版: (2025)

SPRINQL : Sub-optimal demonstrations driven offline imitation learning
由: HOANG, Minh Huy, et al.
出版: (2024)

SIMULATION ANALYTICS FOR INDUSTRIAL APPLICATIONS
由: QIN JIANCHENG
出版: (2023)

REINFORCEMENT LEARNING FOR FINANCIAL STOCHASTIC CONTROL: OPTIMAL MARKET MAKING WITH REBATE AND OPTIMAL LIQUIDATION WITH HIDDEN ORDER
由: ZHANG GE
出版: (2022)

REINFORCEMENT LEARNING BASED SOLUTION APPROACHES FOR INTEGRATED SCHOOL BUS ROUTING AND SCHEDULING PROBLEM
由: EDA KOKSAL AHMED
出版: (2021)

SAMPLE-EFFICIENT AUTOMATED MACHINE LEARNING WITH BAYESIAN OPTIMIZATION
由: DAI ZHONGXIANG
出版: (2021)

APPLICATIONS OF MACHINE LEARNING IN PORTFOLIO OPTIMIZATION AND INTELLECTUAL PROPERTY VALUATION
由: JIANG YIPENG
出版: (2025)

DISPATCHING METHODOLOGIES FOR INTERNAL TRANSPORTATION IN AUTOMATED WAREHOUSE
由: CAI DONGJUN
出版: (2024)

LEARNING-TO-SEARCH APPROACHES FOR VEHICLE ROUTING PROBLEMS USING DEEP REINFORCEMENT LEARNING
由: MA YINING
出版: (2024)

Approximate difference rewards for scalable multigent reinforcement learning
由: SINGH, Arambam James, et al.
出版: (2021)

Cooperative communications in wireless networks : novel approaches in the mac layer
由: GHASEM NADDAF ZADEH SHIRAZI
出版: (2011)

Deep reinforcement learning for UAV routing in the presence of multiple charging stations
由: Fan, Mingfeng, et al.
出版: (2023)

Intelligent adaptive gossip-based broadcast protocol for UAV-MEC using multi-agent deep reinforcement learning
由: REN, Zen, et al.
出版: (2023)

NPE-DRL: enhancing perception constrained obstacle avoidance with non-expert policy guided reinforcement learning
由: Zhang, Yuhang, et al.
出版: (2024)

HIERARCHICAL REINFORCEMENT LEARNING WITH PARAMETERIZED OPTIONS FOR LONG-HORIZON ROBOTIC MANIPULATION
由: GUO CHAOQUN
出版: (2023)

IMPLICIT CURRICULUM IN PROCGEN MADE EXPLICIT
由: TAN ZHENXIONG
出版: (2024)

Guaranteed hierarchical reinforcement learning
由: Ang, Riley Xile
出版: (2024)

ADAPTIVE EDGE SELECTION FOR BLIND IMAGE DEBLURRING
由: YANG LIUGE
出版: (2020)

LEARNING GENERALIZABLE REPRESENTATIONS IN REINFORCEMENT LEARNING
由: WANG, KAIXIN
出版: (2023)

MODEL-BASED REINFORCEMENT LEARNING FOR COMPLEX ENVIRONMENTS
由: MA XIAO
出版: (2022)