SOL is a new hierarchical RL algorithm that reaches 35x higher throughput and outperforms flat agents when trained on 30 billion frames in NetHack while showing positive scaling.
Openai baselines
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
OpenRLHF is a new open-source RLHF framework reporting 1.22x to 1.68x speedups and fewer lines of code than prior systems.
DemPref uses demonstrations to form a coarse reward prior and ground active preference queries, achieving higher efficiency than pure preference learning and higher user preference than IRL in experiments.
citing papers explorer
-
Scalable Option Learning in High-Throughput Environments
SOL is a new hierarchical RL algorithm that reaches 35x higher throughput and outperforms flat agents when trained on 30 billion frames in NetHack while showing positive scaling.
-
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
OpenRLHF is a new open-source RLHF framework reporting 1.22x to 1.68x speedups and fewer lines of code than prior systems.
-
Learning Reward Functions by Integrating Human Demonstrations and Preferences
DemPref uses demonstrations to form a coarse reward prior and ground active preference queries, achieving higher efficiency than pure preference learning and higher user preference than IRL in experiments.