Reinforcement learning with belief maintenance over driver cooperation levels enables successful merging in dense traffic with fewer deadlocks than online planning methods.
Using eligibility traces to find the best memoryless policy in partially observable markov decision processes,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic
Reinforcement learning with belief maintenance over driver cooperation levels enables successful merging in dense traffic with fewer deadlocks than online planning methods.