Line of therapy (LoT); confidence interval (CI); first line of therapy (1L); second line of therapy (2L).
Extended Data Table 2 | Validation on progression-free survival hazard ratioThe number of inclusion and exclusion criteria, the number of eligible patients and the hazard ratio of progression-free survival with confidence interval of emulated aNSCLC trials with eligibility criteria under three scenarios: original criteria of the clinical trial, fully relaxed criteria and data-driven criteria learned from results of the hazard ratio of overall survival (same as in Table 1).
Article Extended Data Table 3 | Analysis in other cancersEligibility criteria for colorectal cancer (CRC), advanced melanoma and metastatic breast cancer in three scenarios. The number of inclusion and exclusion criteria, the number of eligible patients and the hazard ratio of the overall survival with confidence interval of emulated aNSCLC trials with eligibility criteria under three scenarios: original criteria of the clinical trial, fully relaxed criteria and data-driven criteria.
Experience replay is a key technique behind many recent advances in deep reinforcement learning. Allowing the agent to learn from earlier memories can speed up learning and break undesirable temporal correlations. Despite its widespread application, very little is understood about the properties of experience replay. How does the amount of memory kept affect learning dynamics? Does it help to prioritize certain experiences? In this paper, we address these questions by formulating a dynamical systems ODE model of Q-learning with experience replay. We derive analytic solutions of the ODE for a simple setting. We show that even in this very simple setting, the amount of memory kept can substantially affect the agent's performance-too much or too little memory both slow down learning. Moreover, we characterize regimes where prioritized replay harms the agent's learning. We show that our analytic solutions have excellent agreement with experiments. Finally, we propose a simple algorithm for adaptively changing the memory buffer size which achieves consistently good empirical performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.