@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2111.01334,
          title = {Measuring and utilizing temporal network dissimilarity},
          author = {Xiu-Xiu Zhan , Chuang Liu , Zhipeng Wang , Huijuang Wang , Petter Holme , Zi-Ke Zhang}, 
          journal={arXiv preprint arXiv:2111.01334}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2111.01334v1}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2111.01334,
          title = {Measuring and utilizing temporal network dissimilarity},
          author = {Xiu-Xiu Zhan , Chuang Liu , Zhipeng Wang , Huijuang Wang , Petter Holme , Zi-Ke Zhang}, 
          journal={arXiv preprint arXiv:2111.01334}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2111.01334v1}
        }

@article{2110.06553,
          title = {Spatial-temporal Transformers for EEG Emotion Recognition},
          author = {Jiyao Liu , Hao Wu , Li Zhang , Yanxi Zhao}, 
          journal={arXiv preprint arXiv:2110.06553}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2110.06553v2}
        }

@article{1512.07669,
          title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov
  Decision Processes},
          author = {Vikram Krishnamurthy}, 
          journal={arXiv preprint arXiv:1512.07669}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.07669v1}
        }

@article{1511.02377,
          title = {The Value Functions of Markov Decision Processes},
          author = {Ehud Lehrer , Eilon Solan , Omri N. Solan}, 
          journal={arXiv preprint arXiv:1511.02377}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1511.02377v1}
        }

@article{1512.09075,
          title = {A Notation for Markov Decision Processes},
          author = {Philip S. Thomas , Billy Okal}, 
          journal={arXiv preprint arXiv:1512.09075}, 
          year = {2015}, 
          url = {http://arxiv.org/abs/1512.09075v2}
        }

@article{2008.10426,
          title = {Taming denumerable Markov decision processes with decisiveness},
          author = {Nathalie Bertrand , Patricia Bouyer , Thomas Brihaye , Paulin Fournier}, 
          journal={arXiv preprint arXiv:2008.10426}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2008.10426v1}
        }

@article{0711.2185,
          title = {Exact finite approximations of average-cost countable Markov Decision
  Processes},
          author = {Arie Leizarowitz , Adam Shwartz}, 
          journal={arXiv preprint arXiv:0711.2185}, 
          year = {2007}, 
          url = {http://arxiv.org/abs/0711.2185v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2106.01134,
          title = {Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity},
          author = {Wei Liao , Xiaohui Wei , Jizhou Lai}, 
          journal={arXiv preprint arXiv:2106.01134}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.01134v1}
        }

@article{2012.01100,
          title = {Self-correcting Q-Learning},
          author = {Rong Zhu , Mattia Rigotti}, 
          journal={arXiv preprint arXiv:2012.01100}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2012.01100v2}
        }

@article{1703.02102,
          title = {Revisiting stochastic off-policy action-value gradients},
          author = {Yemi Okesanjo , Victor Kofia}, 
          journal={arXiv preprint arXiv:1703.02102}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1703.02102v2}
        }

@article{2209.01820,
          title = {Natural Policy Gradients In Reinforcement Learning Explained},
          author = {W. J. A. van Heeswijk}, 
          journal={arXiv preprint arXiv:2209.01820}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2209.01820v1}
        }

@article{1811.09013,
          title = {An Off-policy Policy Gradient Theorem Using Emphatic Weightings},
          author = {Ehsan Imani , Eric Graves , Martha White}, 
          journal={arXiv preprint arXiv:1811.09013}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1811.09013v2}
        }

@article{1911.04817,
          title = {On Policy Gradients},
          author = {Mattis Manfred Kämmerer}, 
          journal={arXiv preprint arXiv:1911.04817}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1911.04817v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2111.01334,
          title = {Measuring and utilizing temporal network dissimilarity},
          author = {Xiu-Xiu Zhan , Chuang Liu , Zhipeng Wang , Huijuang Wang , Petter Holme , Zi-Ke Zhang}, 
          journal={arXiv preprint arXiv:2111.01334}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2111.01334v1}
        }

@article{2110.06553,
          title = {Spatial-temporal Transformers for EEG Emotion Recognition},
          author = {Jiyao Liu , Hao Wu , Li Zhang , Yanxi Zhao}, 
          journal={arXiv preprint arXiv:2110.06553}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2110.06553v2}
        }

@article{2007.04828,
          title = {Predictability of real temporal networks},
          author = {Disheng Tang , Wenbo Du , Louis Shekhtman , Yijie Wang , Shlomo Havlin , Xianbin Cao , Gang Yan}, 
          journal={arXiv preprint arXiv:2007.04828}, 
          year = {2020}, 
          url = {http://arxiv.org/abs/2007.04828v1}
        }