conftrace_

non-stationary dynamics

4 papers

Explore in graph

Co-occurring keywords

bayesian policy reuse (2) gradient correction (13) hierarchical federated learning (5) model drift (8) human-ai collaboration (117) non-convex optimization (547) meta-task learning (1) hierarchical architecture (55) predictive learning (17) memory module (40)

Papers

Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators NIPS 2024
Hierarchical Federated Learning with Multi-Timescale Gradient Correction NIPS 2024
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning ICML 2021
Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics CVPR 2019