An Introduction to Reinforcement Learning

By Stephen W. Carden. 2013

2,342 citations recorded by the source corpus.

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

Investigating Contingency Awareness Using Atari 2600 Games (2012, methodology): “An -greedy policy (Sutton and Barto 1998) is used, which takes exploratory actions with probability , and otherwise chooses the action estimated to have highest value.”
Counterfactual reasoning and learning systems: the example of computational advertising (2012, methodology): “In particular, the work presented in this section is closely related to the Monte-Carlo approach of reinforcement learning (Sutton and Barto, 1998, chapter 5) and to the offline evaluation of contextual bandit policies (Li et al., 2010, 2011).”
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 notational standard MDPNv1 for Markov decision processes (Thomas, 2015a, MDPs).”
Towards Continual Reinforcement Learning: A Review and Perspectives (2020, methodology): “C) Depicts the backward view of RL where we leverage recent states and rewards to correct our evaluations of past states (from (Sutton and Barto, 1998)).”
Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis (2015, methodology): “Indeed, for the TD(0) algorithm (Sutton and Barto, 1998; corresponding to the β = 0 case in our setting), a similar representation as a projected Bellman operator holds, but it may be shown that in the off-policy setting the algorithm might diverge (Baird 1995).”
Linear Off-Policy Actor-Critic (2012, methodology): “For an appropriate step size αu,t (so that the update to πu′ increases the objective with the action-value function Qπu,γ , fixed as the old action-value function), we can guarantee that Jγ(u) = ∑ s∈S db(s) ∑ a∈A πu(a|s)Qπu,γ(s, a) ≤ ∑ s∈S db(s) ∑ a∈A πu′(a|s)Qπu,γ(s, a) Now we can proceed similarly”
What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study (2020, methodology): “For the case “advantage_estimator (C6) = N-step”, we further sampled the sub-choices: * N-step N (C7): {1, 3, 10, 1000000} –”