LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
arXiv preprint arXiv:2311.00344 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
other 1polarities
unclear 1representative citing papers
MAGELLAN augments LLM agents with online metacognitive LP prediction via semantic generalization to scale curriculum learning in open-ended goal spaces.
Extracting task vectors from offline data to define training task distributions improves zero-shot offline RL performance by an average of 20%.
citing papers explorer
-
Goal-Conditioned Agents that Learn Everything All at Once
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
-
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
MAGELLAN augments LLM agents with online metacognitive LP prediction via semantic generalization to scale curriculum learning in open-ended goal spaces.
-
Improving Zero-Shot Offline RL via Behavioral Task Sampling
Extracting task vectors from offline data to define training task distributions improves zero-shot offline RL performance by an average of 20%.