Learning Algorithms for Markov Decision Processes with Average Cost

By Jinane Abounadi, Dimitri P. Bertsekas, Vivek Shripad Borkar. 2001

242 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhuoran Yang
2. Tong Zhang
3. J. Urgen Schmidhuber
4. Dileep Manisseri Kalathil
5. Rahul Jain
6. William Benjamin Haskell
7. Kaiqing Zhang
8. Tamer Basar

In Computer Networks and Communications

1. J. Urgen Schmidhuber
2. Zhuoran Yang
3. Kaiqing Zhang
4. Tamer Basar
5. Sean P. Meyn
6. Han Liu
7. Vivek Shripad Borkar
8. Tong Zhang

In Statistics and Probability

1. Zhuoran Yang
2. Tamer Basar
3. Kaiqing Zhang
4. Sean P. Meyn
5. J. Urgen Schmidhuber
6. Tong Zhang
7. Han Liu
8. Dileep Manisseri Kalathil

Citations in the corpus

• Deep learning in neural networks: An overview (2014, background): “Many variants of traditional RL exist (e.g., Barto et al., 1983; Watkins, 1989; Watkins and Dayan, 1992; Moore and Atkeson, 1993; Schwartz, 1993; Baird, 1994; Rummery and Niranjan, 1994; Singh, 1994; Baird, 1995; Kaelbling et al., 1995; Peng and Williams, 1996; Mahadevan, 1996; Tsitsiklis and van Ro”
• On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “The parameters or weights of C are trained to maximize reward by a standard RL method such as Q-learning or similar methods [17, 292, 293, 172, 254, 212, 262, 10, 122, 188, 157, 281, 26, 216, 197, 272, 311, 9, 163, 174, 22, 27, 2, 137, 276, 156, 284].”
• Reinforcement Learning: A Tutorial Survey and Recent Advances (2009, unknown): “This result was subsequently pursued for the average-reward algorithms (Abounadi et al., 2001) which also exploited results for non-expansive mappings (Borkar and Soumyanath, 1997).”
• Empirical Dynamic Programming (2013, background): “Q-learning for the average cost case was developed in [1], and in a risk-sensitive context was developed in [10].”
• Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents (2018, background): “It has been a standard assumption in many analyses for two-time-scale reinforcement learning algorithms (Abounadi et al., 2001; Bhatnagar et al., 2009; Degris et al., 2012; Prasad et al., 2014).”
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning (2000, methodology): “For asynchronous algorithms, it is proved for discounted cost only [1, 13, 20], or by introducing a projection to enforce stability [14].”