ライフサイエンスコーパス: reinforcement learning

1 basal ganglia are important for movement and reinforcement learning.

2 separation and conjunctive representation in reinforcement learning.

3 ereas choice bias results from supervised or reinforcement learning.

4 s to reveal their separable contributions to reinforcement learning.

5 gnment with more recent theories of Bayesian reinforcement learning.

6 ap in the quest for the neural mechanisms of reinforcement learning.

7 thms known as "model-based" and "model-free" reinforcement learning.

8 ents a form of spatial credit assignment for reinforcement learning.

9 ty in response to stimuli is a key factor in reinforcement learning.

10 ant consequences for computational models of reinforcement learning.

11 arallel contribution of MB and MF systems in reinforcement learning.

12 roduce effects of dopaminergic medication on reinforcement learning.

13 CC behavioral patterns could be explained by reinforcement learning.

14 mine (DA) and regulates appetitive drive and reinforcement learning.

15 r to deviate sharply from the predictions of reinforcement learning.

16 e algorithmic implementation of imitation in reinforcement learning.

17 udy failed to replicate previous findings on reinforcement learning.

18 ntial hypothesis posits that dopamine biases reinforcement learning.

19 sure may be a critical cellular component of reinforcement learning.

20 licit influence of movement error signals on reinforcement learning.

21 y aging does not significantly impair simple reinforcement learning.

22 "model-free" and "model-based" strategies in reinforcement learning.

23 s: dynamical systems, Bayesian inference and reinforcement learning.

24 ntribution of these regions to probabilistic reinforcement learning.

25 neural control of instrumental behaviors by reinforcement learning.

26 d opposing effects on locomotor behavior and reinforcement learning.

27 riatum where they contribute to movement and reinforcement learning.

28 nisms underlying adaptive imitation in human reinforcement learning.

29 oss, which is associated with impairments in reinforcement learning.

30 h opacities, based on deep learning and deep reinforcement learning.

31 Training is achieved with Deep Reinforcement Learning.

32 a model that combines signal detection with reinforcement learning.

33 from regression to image classification and reinforcement learning.

34 clei that contribute to action selection and reinforcement learning.

35 n striatum, a central node in feedback-based reinforcement learning.

36 recognized to play an important role beyond reinforcement learning.

37 e for a neural realization of distributional reinforcement learning.

38 s, including motivation, motor learning, and reinforcement learning.

39 rameworks such as animal learning theory and reinforcement learning [3-7].

40 Here we describe the use of reinforcement learning(4,5) to create a high-performing

41 cial intelligence research on distributional reinforcement learning(4-6).

42 formalizing our predictions as parameters in reinforcement learning accounts of behaviour.

43 cent evidence indicates that, beyond classic reinforcement learning adaptations, individuals may also

44 We confirm that feedback via a trained reinforcement learning agent can be used to maintain pop

45 A model-free reinforcement learning algorithm revealed that rats with

46 able to other complex domains: a multi-agent reinforcement learning algorithm that uses data from bot

47 s' behaviour was better explained by a basic reinforcement learning algorithm, adults' behaviour inte

48 bine them with model-free, experience-based, reinforcement learning algorithms to train the gliders.

49 aracterized using model-based and model-free reinforcement learning algorithms, respectively.

50 midbrain and the reward prediction errors of reinforcement learning algorithms, which express the dif

51 Explore/exploit decisions were modeled using reinforcement learning algorithms.

52 l prediction errors as defined in model-free reinforcement learning algorithms.

53 al the reward prediction error in model-free reinforcement learning algorithms.

54 Reinforcement learning allows organisms to predict futur

55 We then use both optimal control theory and reinforcement learning alongside a combination of analys

56 In inverse reinforcement learning an observer infers the reward dis

57 MRI, we found that adolescents showed better reinforcement learning and a stronger link between reinf

58 Moreover, the inverse association between reinforcement learning and anhedonia in patients implies

59 Theories of reinforcement learning and approach behavior suggest tha

60 triatal DA D2 receptors (D2Rs) also regulate reinforcement learning and are implicated in glucose-rel

61 This is true for reinforcement learning and decision making (where the la

62 the representation of "state," in studies of reinforcement learning and decision making, and also in

63 ns in the human striatum, a key substrate in reinforcement learning and decision making, are modulate

64 Uncertainty plays a critical role in reinforcement learning and decision making.

65 he curse of dimensionality plagues models of reinforcement learning and decision making.

66 These findings demonstrate specific reinforcement learning and decision-making deficits in b

67 have important implications for theories of reinforcement learning and delay discounting.

68 ershman review concepts and advances in deep reinforcement learning and discuss how these can inform

69 an remember a reward-baited location through reinforcement learning and do so quickly and without req

70 rcement learning and a stronger link between reinforcement learning and episodic memory for rewarding

71 that depression has the strongest effects on reinforcement learning and expectations about the future

72 pamine is thought to play a critical role in reinforcement learning and goal-directed behavior, but i

73 ptive function in this context, and also how reinforcement learning and incentive salience models may

74 prefrontal cortex-basal ganglia circuit for reinforcement learning and is ultimately reflected in do

75 Analyses combined computational reinforcement learning and mixed-effects models of decis

76 ion of corticostriatal circuitry involved in reinforcement learning and motivation, although the inte

77 des a neural basis for persisting effects in reinforcement learning and placebo hypoalgesia.

78 n the dorsal striatum has been implicated in reinforcement learning and regulation of motivation, but

79 Here, we investigate how reinforcement learning and selective attention interact

80 sms that underlie these processes, including reinforcement learning and spike-timing-dependent plasti

81 d role for D3 receptors in select aspects of reinforcement learning and suggest that individual varia

82 emonstrator's value function through inverse reinforcement learning and uses it to bias action select

83 se time (RT) distributions that arise during reinforcement learning and value-based decision-making.

84 We review the evidence from reinforcement-learning and habit-learning studies in TS,

85 erse functions, including reward processing, reinforcement learning, and cognitive control.

86 Dopamine is implicated in reward processing, reinforcement learning, and cognitive control.

87 omputer vision, natural language processing, reinforcement learning, and generalized methods.

88 implications to research on self-projection, reinforcement learning, and predictive-processing models

89 Adopting a reinforcement learning approach, we use Gaussian Process

90 uences for brain and computational models of reinforcement learning are discussed.SIGNIFICANCE STATEM

91 theorists have recently proposed model-based reinforcement learning as a candidate framework.

92 We here propose a representation of reinforcement learning as a stochastic process in finite

93 In particular, we aim to test the role of reinforcement learning as the microscopic mechanism used

94 domain knowledge and iteratively training a reinforcement learning-based chemical graph-set designer

95 nference, and that older adults rely more on reinforcement learning-based predictions than younger ad

96 A novel reinforcement-learning-based approach is applied to acce

97 ipheral glucose levels and glucose-dependent reinforcement learning behaviors and highlight the notio

98 at sensory processing, sequence learning and reinforcement learning, but are limited in their ability

99 the relative influence of the two systems in reinforcement learning, but few studies have manipulated

100 error signal proposed to support model-free reinforcement learning, cached-value errors are typicall

101 showing that individuals adopting a type of reinforcement learning, called aspiration learning, phen

102 Finally, we show that reinforcement learning can directly optimise the output

103 In particular, learning from reward, or reinforcement learning, can be driven by two distinct co

104 uterized conformity task, assumed to rely on reinforcement learning circuits, to 32 patients with sch

105 t multiple sources of uncertainty impinge on reinforcement learning computations: uncertainty about t

106 In several reinforcement learning contexts, such as Pavlovian condi

107 Classical reinforcement learning (CRL) has been widely applied in

108 Reinforcement learning describes how the brain can choos

109 This paper presents the deep reinforcement learning (DRL) framework to estimate the o

110 changes were not associated with deficits in reinforcement learning during an object discrimination r

111 These results demonstrate that reinforcement learning engages both attentional habits a

112 erent types of game and the possibility that reinforcement learning explains observed behavior.

113 Feature-based reinforcement learning fails when the values of individu

114 s indicate the great potential of multiagent reinforcement learning for artificial intelligence resea

115 of an approach from artificial intelligence-reinforcement learning-for the control of co-cultures wi

116 seamlessly accommodated within the standard reinforcement-learning formalism.

117 odel that augments the standard reward-based reinforcement learning formulation by associating a valu

118 s formal description of avoidance within the reinforcement learning framework provides a new means of

119 We further describe a reinforcement learning framework through which the tutor

120 lling can be brought together under a common reinforcement learning framework.

121 rvised learning from human expert games, and reinforcement learning from games of self-play.

122 n to overcome the key technical challenge of reinforcement learning from imperfect data, which has pr

123 escribe inferences based on a combination of reinforcement learning from past feedback and participan

124 sed learning from human expert moves, and by reinforcement learning from self-play.

125 Computational modeling of trial-by-trial reinforcement learning further indicated that lower OFC

126 Although reinforcement learning has been central in explaining pl

127 rch on artificial neural networks trained by reinforcement learning has made it possible to model fun

128 the mesoaccumbal circuit for motivation and reinforcement learning have not yet been examined in pri

129 yield choice patterns similar to model-free reinforcement learning; however, samples can vary from t

130 imply that older adults are only impaired in reinforcement learning if they additionally need to lear

131 ansformation, namely, its ability to enhance reinforcement learning in a dynamic environment.

132 eal an important role for the hippocampus in reinforcement learning in adolescence and suggest that r

133 hoice performance for values learned through reinforcement learning in older adults.

134 l link between IL-6 and striatal RPEs during reinforcement learning in the context of acute psycholog

135 of these tasks ignores important aspects of reinforcement learning in the real world: (a) State spac

136 Here we propose an account of dopamine-based reinforcement learning inspired by recent artificial int

137 ork focused on agent imitation and show that reinforcement learning is a good candidate to explain ma

138 In computer science, reinforcement learning is a powerful framework with whic

139 Overall, reinforcement learning is a promising technique for the

140 These results demonstrate that reinforcement learning is an effective solution to real-

141 Similarly, reinforcement learning is discussed in the context of ro

142 FICANCE STATEMENT In aversive and appetitive reinforcement learning, learned effects show extinction

143 An extensive reinforcement learning literature shows that organisms a

144 al studies, the present results suggest that reinforcement learning may be a major proximate mechanis

145 ing is not accounted for by varying a single reinforcement learning mechanism, but by changing the se

146 egulation as resulting from a self-adjusting reinforcement-learning mechanism that infers latent stat

147 engagement are captured by a self-adjusting reinforcement-learning mechanism that tracks changing en

148 These associations can be attained with reinforcement learning mechanisms using a reward predict

149 iatal plasticity can be induced by classical reinforcement learning mechanisms, and might be central

150 in driving behavior on the basis of classic reinforcement learning mechanisms.

151 emale Long-Evans rats are linked to specific reinforcement-learning mechanisms and are predictive of

152 tational framework was used to elucidate the reinforcement-learning mechanisms that change in adolesc

153 sional action and state spaces than existing reinforcement learning methods to model real-life comple

154 at this new approach is better than baseline reinforcement-learning methods in terms of overall perfo

155 behavior was analyzed using both a standard reinforcement learning model and analysis of choice swit

156 We fit a dual-controller reinforcement learning model and obtained a computationa

157 i delivered at random times and formulated a reinforcement learning model based on belief states.

158 slot machine game play as well as a simpler reinforcement learning model based on the Rescorla-Wagne

159 A reinforcement learning model in which state-action value

160 s behavioral and neural data compared with a reinforcement learning model inspired by rating systems

161 Here, we illustrate that a reinforcement learning model of pain offers a mechanisti

162 mood and anxiety group on a parameter of our reinforcement learning model that characterizes a prepot

163 ask performance was described using a simple reinforcement learning model that dissociates the contri

164 icipants' decisions were best explained by a reinforcement learning model that independently learned

165 To cope with uncertainty, we extended a reinforcement learning model with a belief state about t

166 correlated with the rate of learning and the reinforcement learning model's prediction error.

167 Values of choices, estimated by a reinforcement learning model, were regressed against BOL

168 Our reinforcement learning model-based behavioral study test

169 are better explained in a context-dependent reinforcement learning model.

170 h prediction error signals a Rescorla-Wagner reinforcement-learning model was applied.

171 alance between two dissociable strategies of reinforcement learning: model-free and model-based.

172 their inferences over time, we pitted simple reinforcement learning models against more specific "com

173 ic reinforcement learning task combined with reinforcement learning models and fMRI, we found that ad

174 Reinforcement learning models capture many behavioral an

175 stimuli, not actions.SIGNIFICANCE STATEMENT Reinforcement learning models of the ventral striatum (V

176 Reinforcement learning models postulate that neurons tha

177 Reinforcement learning models provide formal and testabl

178 Reinforcement learning models treat the basal ganglia (B

179 We found that, across different conditions, reinforcement learning models were approximately as accu

180 Reinforcement learning models were used to explicate obs

181 een implemented primarily as state-dependent reinforcement learning models with bias parameters to qu

182 iction errors underlie learning of values in reinforcement learning models, are represented by phasic

183 sk evaluating performance using Bayesian and Reinforcement learning models.

184 Using insights from computational reinforcement-learning models and basic-science studies

185 and food consumption through its effects on reinforcement learning, motivation, and hedonic experien

186 ional mechanisms, model-based and model-free reinforcement learning, neuronally implemented in fronto

187 responding for sucrose pellets and sustained reinforcement learning of glucose-paired flavors.

188 ecting 1) Pavlovian biases in the context of reinforcement learning or 2) hyperprecise prior beliefs

189 ions may relate to abnormal decision making, reinforcement learning or somatic processing in TS.

190 Adolescents and adults carried out a novel reinforcement learning paradigm in which participants le

191 We used a reinforcement learning paradigm with compound rewards an

192 icated that in such an unstable environment, reinforcement learning parameters are downregulated depe

193 We approach this puzzle from a reinforcement learning perspective: what kind of spatial

194 mechanism between model-based and model-free reinforcement learning, placing such a mechanism within

195 eralization of two fundamental operations in reinforcement learning: policy improvement and policy ev

196 Many accounts of decision making and reinforcement learning posit the existence of two distin

197 of tasks previously solved, we can reduce a reinforcement-learning problem to a simpler linear regre

198 reduce the amount of data needed to solve a reinforcement-learning problem.

199 thin two hundred trials and errors, as their reinforcement learning processes interact with metacogni

200 To identify the reinforcement-learning processes that are affected by ch

201 d drug use, may be because of disruptions in reinforcement-learning processes that enable behavior to

202 euroscience and psychology; however, quantum reinforcement learning (QRL), which shows superior perfo

203 vior-reduces positive and increases negative reinforcement learning rates.

204 indings, we observed no group differences in reinforcement-learning related fMRI activation.

205 To test this assumption, we simulated a reinforcement learning (RL) agent equipped with a perfec

206 hrough a process described using model-based reinforcement learning (RL) algorithms.

207 Models of reinforcement learning (RL) are prevalent in the decisio

208 The computational framework of reinforcement learning (RL) has allowed us to both under

209 Reinforcement learning (RL) has shown great success in i

210 We have demonstrated the effectiveness of reinforcement learning (RL) in bluff body flow control p

211 emical spaces were used as training sets for reinforcement learning (RL) in combination with differen

212 Reinforcement learning (RL) in simple instrumental tasks

213 Reinforcement learning (RL) is a framework of particular

214 Reinforcement learning (RL) is the behavioral process of

215 Deep reinforcement learning (RL) methods have driven impressi

216 ping paradigm, where subjects solve multiple reinforcement learning (RL) problems differing in struct

217 Reinforcement learning (RL) refers to the behavioral pro

218 ed fMRI analysis revealed a fractionation of reinforcement learning (RL) signals in the ventral stria

219 g a novel oculomotor paradigm, combined with reinforcement learning (RL) simulations, we show that mo

220 eract during learning.SIGNIFICANCE STATEMENT Reinforcement learning (RL) theory has been remarkably p

221 Contemporary reinforcement learning (RL) theory suggests that potenti

222 Reinforcement learning (RL) theory suggests two classes

223 In this paper, we combine Reinforcement Learning (RL) with Agent Based Modeling (A

224 nymous with the 'reward prediction error' of reinforcement learning (RL), and are thought to update n

225 ble systems, such as working memory (WM) and reinforcement learning (RL), contribute simultaneously t

226 e capacities and, thanks to progress in deep reinforcement learning (RL), it is now possible to apply

227 We review the psychology and neuroscience of reinforcement learning (RL), which has experienced signi

228 ed blocks of stimulus-based and action-based reinforcement learning (RL).

229 ehavior can be characterized as hierarchical reinforcement learning (RL).

230 al, and computational processes that support reinforcement learning (RL).

231 profound neuroscientific implications: deep reinforcement learning (RL).

232 ve reliability of model-based and model-free reinforcement-learning (RL) systems plays a role in the

233 or signals consistent with formal models of "reinforcement learning" (RL) have repeatedly been found

234 ventral tegmental area (VTA) contributes to reinforcement learning, rodent evidence suggests that sl

235 A reinforcement-learning scheme we demonstrate is capable

236 librium, level-k cognition, fictitious play, reinforcement learning, selective payoff-biased imitatio

237 reased ventral striatal RPE signaling during reinforcement learning (session 2), though there was no

238 ons can be regulated via striatally mediated reinforcement learning signals.

239 sing a combination of evolutionary analysis, reinforcement learning simulations, and behavioral exper

240 p to predict expert actions, and (ii) a deep reinforcement learning step to estimate the long-term va

241 ng in dynamic environments requires multiple reinforcement-learning steps that may be implemented by

242 lf-administration independently altered both reinforcement learning strategies.

243 older adults rely more heavily on suboptimal reinforcement-learning strategies supported by the ventr

244 showed worse performance and relied more on reinforcement-learning strategies than younger adults, w

245 proaches for independently quantifying these reinforcement-learning strategies.

246 This is different from the Pavlov, a reinforcement learning strategy promoting mutual coopera

247 ipiprazole on more cognitive facets of human reinforcement learning, such as learning from the forgon

248 We argue that recent models of reinforcement learning suggest that temporal updating mu

249 gests an imbalance in the influence of these reinforcement learning systems on behavior in individual

250 These complementary reinforcement-learning systems can be characterized comp

251 Using a probabilistic reinforcement learning task combined with reinforcement

252 his, we used a modified version of a classic reinforcement learning task in which feedback indicated

253 We tested subjects in a reinforcement learning task in which reward size and pro

254 e and female) completed multiple blocks of a reinforcement learning task that contained a global hier

255 n counterfactual learning, we administered a reinforcement learning task that involves both direct le

256 supports the transition to exploitation on a reinforcement learning task with a spatially structured

257 retrospectively predicted performance on the reinforcement learning task, demonstrating that the bias

258 During a reinforcement learning task, the information content of

259 event-related potentials in humans during a reinforcement learning task, we show strong evidence in

260 Participants then performed a reinforcement learning task, which simultaneously probes

261 of value representation following a standard reinforcement learning task.

262 ) while monkeys performed a two-armed bandit reinforcement learning task.

263 N = 44) featuring a new variant of a social reinforcement learning task.

264 al variability in behavioural responses to a reinforcement-learning task encompassing a novelty manip

265 umbens activation in a simple unidimensional reinforcement-learning task was not significantly affect

266 and decision speed in a two-stage sequential reinforcement-learning task.

267 ey behavioural responses associated with the reinforcement-learning task.

268 performance of two groups of participants on reinforcement learning tasks using a computational model

269 Contrary to previous results in reinforcement learning tasks, individuals with moderate

270 knowledge of chemistry and state-of-the-art reinforcement learning techniques (double Q-learning and

271 ices of older adults are better predicted by reinforcement learning than Bayesian inference, and that

272 Q-learning is a method of reinforcement learning that employs backwards stagewise

273 In the framework of reinforcement learning, the probability of performing an

274 ular decision-making task used in studies of reinforcement learning, the two-armed bandit task.

275 Does learning in human observers comply with reinforcement learning theories, which describe how subj

276 Our results consolidate reinforcement learning theory and striatal RPEs as key f

277 Reinforcement learning theory has provided insight into

278 Reinforcement learning theory powerfully characterizes h

279 re abnormal with respect to predictions from reinforcement learning theory were associated with lower

280 d prediction errors (RPEs), a key concept of reinforcement learning theory, are crucial to the format

281 This view, rooted in reinforcement learning theory, equates motor variability

282 Using computational modeling based on reinforcement learning theory, we found that conditionin

283 Wagner learning rule, a finding predicted by reinforcement learning theory.

284 Reinforcement-learning theory distinguishes between stim

285 is no doubt that social signals affect human reinforcement learning, there is still no consensus abou

286 rationalization and theory of mind, inverse reinforcement learning, thought experiments, and reflect

287 ncode reward prediction errors and can drive reinforcement learning through their projections to stri

288 ate their expectations after playing a DG by reinforcement learning to construct a model that explain

289 the DG and also to the wide applicability of reinforcement learning to explain many strategic interac

290 stinction between model-based and model-free reinforcement learning to investigate the unique and sha

291 The circuits modified during such reinforcement learning to support decision-making are no

292 In turn, selective attention biases reinforcement learning towards relevant dimensions of th

293 By adapting computational models of reinforcement learning, we assessed the influence of con

294 of accumulation-to-bound decision models and reinforcement learning, we modeled the performance of hu

295 on, we extend our model with multi-objective reinforcement learning, which maximizes drug-likeness wh

296 f the environment by combining principles of reinforcement learning with accumulation-to-bound models

297 The combination of reinforcement learning with deep learning is a promising

298 physiological (pupil dilation) signatures of reinforcement learning with eligibility trace across mul

299 n a single task, adapting a standard task of reinforcement learning with incidental episodic encoding

300 re we introduce an algorithm based solely on reinforcement learning, without human data, guidance or