Co-training an SDC and 12 pedestrians with MAPPO in a MARL setup yields 78% goal success and 14% collisions versus 35% goals and 33% for the best rule-based baseline, with jaywalking linked to 62% of collisions despite being only 13% of events.
Counterfactual multi-agent policy gradients,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
Co-training an SDC and 12 pedestrians with MAPPO in a MARL setup yields 78% goal success and 14% collisions versus 35% goals and 33% for the best rule-based baseline, with jaywalking linked to 62% of collisions despite being only 13% of events.