Task-Aware Verifiable RNN-Based Policies for Partially Observable Markov Decision Processes
From MaRDI portal
Publication:5026215
DOI10.1613/jair.1.12963OpenAlexW3215640983WikidataQ113424377 ScholiaQ113424377MaRDI QIDQ5026215
Ufuk Topcu, Steven Carr, Nils Jansen
Publication date: 7 February 2022
Published in: Journal of Artificial Intelligence Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1613/jair.1.12963
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Planning and acting in partially observable stochastic domains
- Optimal cost almost-sure reachability in POMDPs
- Minimal counterexamples for linear-time probabilistic verification
- Enforcing almost-sure reachability in POMDPs
- Verification and control of partially observable probabilistic systems
- Simple statistical gradient-following algorithms for connectionist reinforcement learning
- Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network
- Safety verification of deep neural networks
- Reluplex: an efficient SMT solver for verifying deep neural networks
- An SMT-based approach for verifying binarized neural networks
- The complexity of reachability in parametric Markov decision processes
- Handbook of Model Checking
- Probabilistic ω-automata
- Elements of Information Theory
This page was built for publication: Task-Aware Verifiable RNN-Based Policies for Partially Observable Markov Decision Processes
