A reverse world model trained on reversed replay data generates counterfactual prior states that significantly help non-experts identify why a model-based RL agent failed.
World models
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
-
Explainable Reinforcement Learning Agents Using World Models
A reverse world model trained on reversed replay data generates counterfactual prior states that significantly help non-experts identify why a model-based RL agent failed.