Reinforcement learning

By Andrew Barto. 1998

How researchers see this paper

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

In Reinforcement Learning

Citations in the corpus

Value-Decomposition Networks For Cooperative Multi-Agent Learning (2017, methodology): “We recall some key concepts of the RL setting (Sutton and Barto, 1998), an agent-environment framework (Russell and Norvig, 2010) in which an agent sequentially interacts with the environment over a sequence of timesteps, t = 1 , 2 , 3 , . . . , by executing actions and receiving observations and…”
Deep learning in neural networks: An overview (2014, neutral): “This assumption does not hold in the broader fields of Sequential Decision Making and Reinforcement Learning (RL) (Hutter, 2005; Kaelbling, Littman, & Moore, 1996; Sutton & Barto, 1998; Wiering & van Otterlo, 2012) (Section 6).”
Reinforcement learning in robotics: A survey (2013, methodology): “One example is tile coding (Sutton and Barto, 1998), where the space is subdivided into (potentially irregularly shaped) regions, called tiling.”
Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning (2016, methodology): “We assume that the reader is familiar with reinforcement learning (Sutton & Barto, 1998) and adopt nota-tional standard MDPNv1 for Markov decision processes (Thomas, 2015a, MDPs).”
On Convergence of Emphatic Temporal-Difference Learning (2015, methodology): “For the details of this Bellman equation, we refer the readers to the early work (Sutton, 1995; Sutton and Barto, 1998) and the recent work (Sutton et al., 2015).”
Tag-Trigger-Consolidation: A Model of Early and Late Long-Term-Potentiation and Depression (2008, background): “[52] which can be interpreted as a synapse specific tag.”
Policy Networks with Two-Stage Training for Dialogue Systems (2016, background): “tion 7 concludes the paper and makes suggestions for future research. 1Teacher DA2C 2 Preliminaries The reinforcement learning problem consists of an environment (the user) and an agent (the system) (Sutton and Barto, 1998). The environment is described as a set of continuous or discrete states S an”
Batch Mode Reinforcement Learning based on the Synthesis of Artificial Trajectories (2012, methodology): “Optimal control problems arise in many real-life applications, such as engineering (Ried-miller 2005), medicine (Robins 1986; Murphy et al. 2001; Murphy 2003) or artiﬁcial intelligence (Sutton and Barto 1998).”
Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems (2009, methodology): “Reinforcement Learning (RL) provides a principled, data-driven optimisation framework for our type of planning problem (Sutton and Barto, 1998).”
WRITING MEMORIES WITH LIGHT-ADDRESSABLE REINFORCEMENT CIRCUITRY (2009, methodology): “…machine learning (Samuel, 1959; Holland, 1986; Sutton and Barto, 1998), and psychologists (Rescorla and Wagner, 1972) have developed models of adaptive behavior in which error signals play a central role; they have also designed efficient algorithms for their computation (Sutton and Barto, 1998).”
Toward an Integration of Deep Learning and Neuroscience (2016, methodology): “…assignment 28 Many other reinforcement learning algorithms, including REINFORCE (Williams, 1992), can be implemented as fully online algorithms using “eligibility traces,” which accumulate the sensitivity of action distributions to parameters in a temporally local manner (Sutton and Barto, 1998).”
Gaussian Processes in Reinforcement Learning (2003, background): “…the probability of taking action a in state s, and P a s,s is the transition probability of going to state s when applying action a given that we are in state s, R a s,s denotes the immediate expected reward and 0 γ 1 is the discount factor (see Sutton and Barto (1998) for a thorough review).”