@article {GruberENEURO.0167-16.2016, author = {Aaron J. Gruber and Rajat Thapa}, title = {The memory trace supporting lose-shift responding decays rapidly after reward omission and is distinct from other learning mechanisms in rats}, elocation-id = {ENEURO.0167-16.2016}, year = {2016}, doi = {10.1523/ENEURO.0167-16.2016}, publisher = {Society for Neuroscience}, abstract = {The propensity of animals to shift choices immediately after unexpectedly poor reinforcement outcomes is a pervasive strategy across species and tasks. We report here that the memory supporting such lose-shift responding in rats rapidly decays during the inter-trial interval and persists throughout training and testing on a binary choice task, despite being a sub-optimal strategy. Lose-shift responding is not positively correlated with the prevalence and temporal dependence of win-stay responding, and it is inconsistent with predictions of reinforcement learning on the task. These data provide further evidence that win-stay and lose-shift are mediated by dissociated neural mechanisms, and indicate that lose-shift responding presents a potential confound for the study of choice in the many operant choice tasks with short inter-trial-intervals. We propose that this immediate lose-shift responding is an intrinsic feature of the brain{\textquoteright}s choice mechanisms that is engaged as a choice reflex, and works in parallel with reinforcement learning and other control mechanisms to guide action selection.Significance Statement: The brain appears to use several neural systems that operate in parallel to control decisions. We provide very strong evidence here that a decision system compelling rats to shift responses after bad outcomes strongly influences decisions for several seconds following reward omission, and that its properties are distinct from other decision systems, such as those compelling rats to repeat decisions leading to good outcomes. This shift system is prevalent from the first day of training, and its properties are remarkably stable over weeks of testing. We suggest that it may be an immutable choice reflex that strongly influences decisions in the seconds after reward omission to briefly augment the output of other reinforcement learning systems.}, URL = {https://www.eneuro.org/content/early/2016/11/08/ENEURO.0167-16.2016}, eprint = {https://www.eneuro.org/content/early/2016/11/08/ENEURO.0167-16.2016.full.pdf}, journal = {eNeuro} }