An Idiosyncrasy of Time-discretization in Reinforcement Learning
Many reinforcement learning algorithms are built on an assumption that an agent interacts with an environment over fixed-duration, discrete time steps. However, physical systems are continuous in time, requiring a choice of time-discretization granularity when digitally controlling them. Furthermore, such systems do not wait for decisions to be made before advancing the environment state, necessitating the study of how the choice of discretization may affect a reinforcement learning algorithm. In this work, we consider the relationship between the definitions of the continuous-time and discrete-time returns. Specifically, we acknowledge an idiosyncrasy with naively applying a discrete-time algorithm to a discretized continuous-time environment, and note how a simple modification can better align the return definitions. This observation is of practical consideration when dealing with environments where time-discretization granularity is a choice, or situations where such granularity is inherently stochastic.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis
In this paper, we work on intra-variable handwriting, where the writing samples of an individual can vary significantly. Such within-writer variation throws a challenge for automatic writer inspection, where the state-of…
Reinforcement LearningTripletClassification of Multiword Expressions in Malayalam
Multiword expression is an interesting concept in languages and the MWEs of a language are not easy for a non-native speaker to understand. It includes lexicalized phrases, idioms, collocations etc. Data on multiwords ar…
ClassificationModeling the Statistical Idiosyncrasy of Multiword Expressions
Actor-Critic with variable time discretization via sustained actions
Reinforcement learning (RL) methods work in discrete time. In order to apply RL to inherently continuous problems like robotic control, a specific time discretization needs to be defined. This is a choice between sparse …
Reinforcement Learning (RL)Safeguarding Learning-based Control for Smart Energy Systems with Sampling Specifications
We study challenges using reinforcement learning in controlling energy systems, where apart from performance requirements, one has additional safety requirements such as avoiding blackouts. We detail how these safety req…
reinforcement-learningReinforcement LearningSafe Reinforcement Learning