Continual Learning in the Teacher-Student Setup: Impact of Task Similarity 2022 ICML Formalizing the Generalization-Forgetting Trade-off in Continual Learning 2021 NeurIPS A PAC-Bayesian Bound for Lifelong Learning 2014 ICMLForgetting in Foundation Models[...
Model-Based Transfer Learning for Contextual Reinforcement Learning Jung-Hoon Cho, Vindula Jayawardana, Sirui Li, Cathy Wu Key: bayesian optimization, contextual rl ExpEnv: gaussian process, traffic signal, eco-driving, advisory autonomy, control tasks Rethinking Model-based, Policy-based, and Value-...
In recent years, reinforcement learning (RL) systems have shown impressive performance and remarkable achievements. Many achievements can be attributed to
The definition of PAC learnability contains two approximation parameters. The accuracy parameterεdetermines how far the output classifier can be from the optimal one (this corresponds to the “approximately correct” part of “PAC”), and a confidence parameter δ indicating how likely the classifier...
“PAC”). In short, the goal of a PAC-learner is to build a hypothesis with high probability (1-δ) that is approximately correct (error rate less thanε). Knowing that a target concept C is PAC-learnable allows us to bound the sample size necessary to probably learn an approximately ...
Lifelong Machine Learning, Zhiyuan Chen and Bing Liu. (2018). Recent Advances in Open Set Recognition: A Survey, Geng C, Huang S, Chen S. (arXiv, 2018). Recent Advances in Open Set Recognition: A Survey v2, Chuanxing Geng, Sheng-jun Huang, Songcan Chen. (arXiv, 2019). ...
Model-based Lifelong Reinforcement Learning with Bayesian Exploration(Poster: 7, 6, 6) Haotian Fu, Shangqun Yu, Michael Littman, George Konidaris Key: hierarchical Bayesian posterior ExpEnv: HiP-MDP versions of Mujoco, Meta-world On the Statistical Efficiency of Reward-Free Exploration in Non-Line...
A new criterion for domain adaptation 提出一种新的可以强化domain adaptation表现的度量 20181219 arXiv PAC Learning Guarantees Under Covariate Shift PAC learning theory for covariate shift Covariate shift问题的PAC学习理论 20181206 arXiv Transferring Knowledge across Learning Processes Transfer lear...
BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty. Théo Guénais, Dimitris Vamvourellis, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan. (ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning) Contrastive Training for Improved Out-of-Distribution Detection. Jim Winkens, Ru...
Model-Based Transfer Learning for Contextual Reinforcement Learning Jung-Hoon Cho, Vindula Jayawardana, Sirui Li, Cathy Wu Key: bayesian optimization, contextual rl ExpEnv: gaussian process, traffic signal, eco-driving, advisory autonomy, control tasks Rethinking Model-based, Policy-based, and Value-...