Agents that receive LLM-extracted environment rules as context or rewards explore more purposefully and score higher in the Crafter game.
Routledge, 2013
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Laws to Motivation: Guiding Exploration through Law-Based Reasoning and Rewards
Agents that receive LLM-extracted environment rules as context or rewards explore more purposefully and score higher in the Crafter game.