[go: up one dir, main page]

Wabartha et al., 2023 - Google Patents

Piecewise linear parametrization of policies: Towards interpretable deep reinforcement learning

Wabartha et al., 2023

View PDF
Document ID
17760499277202009526
Author
Wabartha M
Pineau J
Publication year
Publication venue
The Twelfth International Conference on Learning Representations

External Links

Snippet

Learning inherently interpretable policies is a central challenge in the path to developing autonomous agents that humans can trust. We argue for the use of policies that are piecewise-linear. We carefully study to what extent they can retain the interpretable …
Continue reading at drive.google.com (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/02—Knowledge representation
    • G06N5/022—Knowledge engineering, knowledge acquisition
    • G06N5/025—Extracting rules from data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/04—Inference methods or devices
    • G06N5/046—Forward inferencing, production systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/04—Inference methods or devices
    • G06N5/043—Distributed expert systems, blackboards
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/12—Computer systems based on biological models using genetic models
    • G06N3/126—Genetic algorithms, i.e. information processing using digital simulations of the genetic system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6217—Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06K9/6232—Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods
    • G06K9/6247—Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods based on an approximation criterion, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/004—Artificial life, i.e. computers simulating life
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computer systems based on specific mathematical models
    • G06N7/005—Probabilistic networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6267—Classification techniques
    • G06K9/6279—Classification techniques relating to the number of classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6267—Classification techniques
    • G06K9/6268—Classification techniques relating to the classification paradigm, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/18—Digital computers in general; Data processing equipment in general in which a programme is changed according to experience gained by the computer itself during a complete run; Learning machines

Similar Documents

Publication Publication Date Title
Harb et al. When waiting is not an option: Learning options with a deliberation cost
Wang et al. Deep reinforcement learning: A survey
Eysenbach et al. Robust predictable control
Le et al. A deep hierarchical reinforcement learning algorithm in partially observable Markov decision processes
Fenjiro et al. Deep reinforcement learning overview of the state of the art
Lang et al. Exploration in relational domains for model-based reinforcement learning
Wickramasinghe et al. Continual learning: A review of techniques, challenges, and future directions
Skowron et al. Information systems in modeling interactive computations on granules
Mohan et al. Structure in deep reinforcement learning: A survey and open problems
de Lope et al. Response threshold models and stochastic learning automata for self-coordination of heterogeneous multi-task distribution in multi-robot systems
Wabartha et al. Piecewise linear parametrization of policies: Towards interpretable deep reinforcement learning
Wang et al. A language measure for performance evaluation of discrete-event supervisory control systems
Zhu et al. Extracting decision tree from trained deep reinforcement learning in traffic signal control
Liu et al. IWOA-RNN: An improved whale optimization algorithm with recurrent neural networks for traffic flow prediction
Skowron et al. Toward interactive computations: A rough-granular approach
Klissarov et al. Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning
Mousavi et al. Automatic abstraction controller in reinforcement learning agent via automata
Herath Evolution and Advancements from Neural Network to Deep Learning
Haas Tutorial: Artificial Neural Networks for Discrete-Event Simulation
Rohrer An implemented architecture for feature creation and general reinforcement learning.
Bharti et al. QL-SSA: An adaptive Q-learning based squirrel search algorithm for feature selection
Djurdjevic et al. Deep belief network for modeling hierarchical reinforcement learning policies
Cohen et al. Integrating distributed component-based systems through deep reinforcement learning
Koola et al. How do we train a stone to think? A review of machine intelligence and its implications
Luttner Training of Neural Networks with Uncertain Data: A Mixture of Experts Approach