Task-Aware Verifiable RNN-Based Policies for Partially Observable Markov Decision Processes (Q5026215): Difference between revisions

From MaRDI portal
Created claim: Wikidata QID (P12): Q113424377, #quickstatements; #temporary_batch_1711626644914
ReferenceBot (talk | contribs)
Changed an Item
 
Property / cites work
 
Property / cites work: An SMT-based approach for verifying binarized neural networks / rank
 
Normal rank
Property / cites work
 
Property / cites work: Probabilistic ω-automata / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5322945 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Optimal cost almost-sure reachability in POMDPs / rank
 
Normal rank
Property / cites work
 
Property / cites work: Handbook of Model Checking / rank
 
Normal rank
Property / cites work
 
Property / cites work: Elements of Information Theory / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5270493 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Safety verification of deep neural networks / rank
 
Normal rank
Property / cites work
 
Property / cites work: Enforcing almost-sure reachability in POMDPs / rank
 
Normal rank
Property / cites work
 
Property / cites work: The complexity of reachability in parametric Markov decision processes / rank
 
Normal rank
Property / cites work
 
Property / cites work: Planning and acting in partially observable stochastic domains / rank
 
Normal rank
Property / cites work
 
Property / cites work: Reluplex: an efficient SMT solver for verifying deep neural networks / rank
 
Normal rank
Property / cites work
 
Property / cites work: Verification and control of partially observable probabilistic systems / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4315289 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5715714 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Simple statistical gradient-following algorithms for connectionist reinforcement learning / rank
 
Normal rank
Property / cites work
 
Property / cites work: Minimal counterexamples for linear-time probabilistic verification / rank
 
Normal rank

Latest revision as of 22:26, 27 July 2024

scientific article; zbMATH DE number 7470366
Language Label Description Also known as
English
Task-Aware Verifiable RNN-Based Policies for Partially Observable Markov Decision Processes
scientific article; zbMATH DE number 7470366

    Statements

    Task-Aware Verifiable RNN-Based Policies for Partially Observable Markov Decision Processes (English)
    0 references
    0 references
    0 references
    0 references
    7 February 2022
    0 references
    Markov decision processes
    0 references
    neural networks
    0 references
    uncertainty
    0 references
    0 references
    0 references
    0 references
    0 references

    Identifiers