DNA trains local Q-learning policies on corridor-shaped subproblems to produce provably epsilon-optimal, behaviorally diverse trajectory options for an RL agent.
Towards explainable road navigation systems
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
-
"What are my options?": Explaining RL Agents with Diverse Near-Optimal Alternatives (Extended)
DNA trains local Q-learning policies on corridor-shaped subproblems to produce provably epsilon-optimal, behaviorally diverse trajectory options for an RL agent.