Education
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert.
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert.
Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation
The main idea is to use a generator to synthesize data for training the student.
Human-AI Shared Control via Policy Dissection
Human-AI shared control allows human to interact and collaborate with autonomous agents to accomplish control tasks in complex environments.
DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection Gang Li
However, the "sparse-to-dense" paradigm complicates the pipeline of SSOD, and
FedPop: A Bayesian Approach for Personalised Federated Learning
Personalised federated learning (FL) aims at collaboratively learning a machine learning model tailored for each client.