Interpolation in the eXtended Classifier System: An architectural perspective

Stein, Anthony; Rauh, Dominik; Tomforde, Sven; Hhner, Jrg

doi:10.1016/j.sysarc.2017.01.010

Cited by 29 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work draws on the methods proposed in [20][21][22][23][24]. The authors used interpolation in combination with an XCS classifier System to speed up learning in single-step problems by using previous experiences as sampling points for interpolation.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments

2021

Self Cite

View full text Add to dashboard Cite

State-of-the-art Deep Reinforcement Learning Algorithms such as DQN and DDPG use the concept of a replay buffer called Experience Replay. The default usage contains only the experiences that have been gathered over the runtime. We propose a method called Interpolated Experience Replay that uses stored (real) transitions to create synthetic ones to assist the learner. In this first approach to this field, we limit ourselves to discrete and non-deterministic environments and use a simple equally weighted average of the reward in combination with observed follow-up states. We could demonstrate a significantly improved overall mean average in comparison to a DQN network with vanilla Experience Replay on the discrete and non-deterministic FrozenLake8x8-v0 environment.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Stein et al introduce their Interpolation Component (IC) in [22]. As already mentioned in Section 3, we adopted it for our approach.…”

Section: Interpolation Componentmentioning

confidence: 99%

Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Following this results we try to achieve a broad distribution over the state space utilizing synthetic experiences. (Stein et al, 2017;Stein et al, 2018) use interpolation in combination with XCS Classifier System to speed up learning in single-step problems by means of using previous experiences as sampling points for interpolation. The used component for interpolation is part of this work and discussed in more detail in section 4.3.…”

Section: Related Workmentioning

confidence: 99%

“…Stein et al introduce their IC (Stein et al, 2017) that this work uses as underlying basic structure for its interpolation tasks. This IC serves as an abstract pattern and consists of a Machine Learning Interface (MLI), an Interpolant, an Adjustment Component, an Evaluation Component and the Sampling Points (SP).…”

Section: Interpolation Componentmentioning

confidence: 99%

Bootstrapping a DQN Replay Memory with Synthetic Experiences

Pilchau

Stein

Hähner

2020

Proceedings of the 12th International Joint Conference on Computational Intelligence

Self Cite

View full text Add to dashboard Cite

An important component of many Deep Reinforcement Learning algorithms is the Experience Replay that serves as a storage mechanism or memory of experienced transitions. These experiences are used for training and help the agent to stably find the perfect trajectory through the problem space. The classic Experience Replay however makes only use of the experiences it actually made, but the stored transitions bear great potential in form of knowledge about the problem that can be extracted. The gathered knowledge contains state-transitions and received rewards that can be utilized to approximate a model of the environment. We present an algorithm that creates synthetic experiences in a nondeterministic discrete environment to assist the learner with augmented training data. The Interpolated Experience Replay is evaluated on the FrozenLake environment and we show that it can achieve a 17% increased mean reward compared to the classic version.

show abstract

“…To fill existing knowledge gaps, as formerly defined by Stein et al (Stein et al, 2018), active learning (Cohn et al, 1994) can be employed (Stein et al, 2017a). In addition we will expect to be able to use interpolation between known classifiers to gain knowledge on inter-laying classifiers (Stein et al, 2016;Stein et al, 2017b). Figure 4 illustrates the basic procedure.…”

Section: Learning Quality Prediction and Strategy Selectionmentioning

confidence: 99%

Towards Automated Parameter Optimisation of Machinery by Persisting Expert Knowledge

Nordsieck

Heider

Angerer

et al. 2019

Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics

Self Cite

View full text Add to dashboard Cite

Commissioning of machines takes up a considerable share of time and money of the total cost of developing a machine. Our project aims at developing an approach to decrease the time needed to commission machines by automating parameter optimisation with the help of formalised expert knowledge. The approach will be developed on the Fused Deposition Modelling (FDM) process, which is an additive manufacturing technique. We pay particular attention to keeping the approach sufficiently abstract to be applied to machines from other domains to benefit its industrial application.

show abstract

Interpolation in the eXtended Classifier System: An architectural perspective

Cited by 29 publications

References 23 publications

Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments

Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments

Bootstrapping a DQN Replay Memory with Synthetic Experiences

Towards Automated Parameter Optimisation of Machinery by Persisting Expert Knowledge

Contact Info

Product

Resources

About