Theory-Inspired Parameter Control Benchmarks for DAC Permalink
TL;DR: New toy benchmarks enable better study of RL agents performance and allows us to compare against ground truth optimal policies.
Recent Posts
Self-Paced Context Evaluation for Contextual Reinforcement Learning Permalink
TL;DR: We propose SPaCE, a general approach that can be deployed for any agent with a value function and task instances identified by their context without a...
AutoRL: AutoML for RL Permalink
TL;DR: An overview of research on AutoRL in 2021 by the AutoML Freiburg group.