LLM-generated code produces compact multi-dimensional latent rewards that improve temporal and multi-agent credit assignment in episodic reinforcement learning, outperforming standard return-decomposition baselines and sometimes dense-reward training.
Title resolution pending
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
-
Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
LLM-generated code produces compact multi-dimensional latent rewards that improve temporal and multi-agent credit assignment in episodic reinforcement learning, outperforming standard return-decomposition baselines and sometimes dense-reward training.