Adaptive Treatment of Epilepsy via Batch-mode Reinforcement Learning

By Arthur Guez, Robert D. Vincent, Massimo Avoli, Joelle Pineau. 2008

107 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Medical & Health AI

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

In Medical & Health AI

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “, 2018), treatment of chronic disorders including epilepsy (Guez et al., 2008), for HIV therapy (Parbhoo et al.”
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (2020, methodology): “Outside of ICU settings, offline RL applications include learning from recordings of seizure activity in mouse brains in order to determine optimal stimulation frequencies for reducing epileptic seizures (Guez et al., 2008).”
Reinforcement Learning in Healthcare: A Survey (2019, methodology): “Guez et al. [76, 77, 182] applied the BRL method, FQI-ERT, to optimize a deep-brain stimulation strategy for the treatment of epilepsy.”
Safe Policy Improvement with Soft Baseline Bootstrapping (2019, background): “…that naturally fit a setting where data collection and optimization are decoupled (contrary to online learning which integrates the two): e.g. dialogue systems (Singh et al., 1999), technical process control (Ernst et al., 2005; Riedmiller, 2005), medical applications (Guez et al., 2008).”
Safe Policy Improvement with Baseline Bootstrapping (2017, neutral): “, 2005; Riedmiller, 2005), medical applications (Guez et al., 2008).”
Informing sequential clinical decision-making through reinforcement learning: an empirical study (2010, background): “There has been a surge of interest in recent years within the medical community regarding the application of Reinforcement Learning (RL) techniques to optimize treatment policies (Thall and Wathan 2000; Ernst et al. 2006; Murphy et al. 2007; Guez et al. 2008; Zhao et al. 2009).”
Benchmarking Batch Deep Reinforcement Learning Algorithms (2019, background): “cting with the environment [Lange et al., 2012]. Learning with ﬁnite data sets is invaluable for a variety of real-world applications, where data collection may be difﬁcult, time-consuming or costly [Guez et al., 2008, Pietquin et al., 2011, Gauci et al., 2018]. In principle, standard off-policy dee”
Batch Mode Reinforcement Learning based on the Synthesis of Artificial Trajectories (2012, background): “…Bonarini et al. 2008; Tognetti et al. 2009), power systems (Ernst et al. 2009), image processing (Ernst et al. 2006a), water reservoir optimization (Castelletti et al. 2007, 2010), medicine (Murphy 2003; Ernst et al. 2006b; Guez et al. 2008) and driving assistance strategies (Pietquin et al. 2011).”
Reinforcement Learning Strategies for Clinical Trials in Non-small Cell Lung Cancer (2011, methodology): “For instance, using random forest or extremely randomized trees (ERT) techniques is very effective for extracting well-fitted Q functions (Ernst, Geurts, and Wehenkel, 2005; Geurts, Ernst, and Wehenkel, 2006; Guez et al., 2008; Zhao et al., 2009).”
Reinforcement learning for closed-loop propofol anesthesia: a study in human volunteers (2014, background): “…et al., 2008) and planning tasks, such as scheduling of HIV therapy (Ernst et al., 2006), optimizing deep-brain stimulation in epilepsy treatment (Guez et al., 2008), dosing strategies for anemia management in patients with chronic renal failure (Mart́ın-Guerrero et al., 2009; Gaweda et al.,…”
Adaptive Control of Epileptic Seizures using Reinforcement Learning (2010, result): “We have already investigated a similar problem in a slightly different experimental setup (amygdala stimulation and perirhinal cortex recording), but our results were limited to offline measures [29].”
Offline policy evaluation across representations with applications to educational games (2014, methodology): “An alternate approach is to use a complex set of input features, and use value function approximation over the feature set; however, this still requires choosing the right combination of input features and function approximator [10, 8].”
Reinforcement Learning based Recommender Systems: A Survey (2021, background): “This made it possible to apply RL in problems with enormous state and action spaces, including self-driving cars [9, 10], robotics [11], industry automation [12], finance [13], healthcare [14, 15], and RSs.”
Bias Correction and Confidence Intervals for Fitted Q-iteration (2008, background): “The problem of learning a good treatment policy from a training set of finite-horizon trajectories generated by a known behavior policy often arises in medical applications [1, 2, 3, 4].”
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models (2019, methodology): “, 2017) to epilepsy (Guez et al., 2008) and sepsis (Komorowski et al.”
Adaptive treatment of anemia on hemodialysis patients: A reinforcement learning approach (2011, methodology): “the design of ATS has been recently applied to the treatment of chronic psychiatric disorders [10], epilepsy [11] or lung cancer”
Convergent Fitted Value Iteration with Linear Function Approximation (2011, background): “In these settings, data gathered from controlled trials can still be used to learn good policies [11, 19].”