A learning-adapting-acting framework that uses an LLM to build and update a causal graph of the game world, then uses that graph to generate goals and shape rewards for an RL agent in Crafter.
Guiding pretraining in reinforcement learning with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting
A learning-adapting-acting framework that uses an LLM to build and update a causal graph of the game world, then uses that graph to generate goals and shape rewards for an RL agent in Crafter.