An LM-driven feedback loop that tunes reward weights from scalar performance statistics reaches 80.4% lap success in a racing task, close to a human expert's peak of 93.6%.
• Adjust values to encourage the agent to complete the goal properly rather than remaining close to it
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games
An LM-driven feedback loop that tunes reward weights from scalar performance statistics reaches 80.4% lap success in a racing task, close to a human expert's peak of 93.6%.