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:2306.01711 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
LLMs diverge from human goal selection in self-directed learning by exploiting single solutions with low variability across instances.
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.
-
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
-
Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task
LLMs diverge from human goal selection in self-directed learning by exploiting single solutions with low variability across instances.