CL-MARL uses an adaptive curriculum scheduler called FlexDiff and Counterfactual Group Relative Policy Advantage to break static-difficulty training in MARL and achieve higher win rates on hard StarCraft maps.
Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Proposes hierarchical MARL framework enforcing safety via constraint manifold at low level with theoretical guarantees and stationary dynamics for stable training and generalization.
Marope applies hierarchical MARL with decentralized lower-level rope policies and a centralized scheduler to achieve cooperative long rope skipping on Unitree G1 humanoids in simulation and reality.
SCALE-COMM uses contrastive alignment on latent embeddings to decouple and stabilize communication learning from policy optimization in decentralized MARL, showing gains on benchmarks and a warehouse task.
Co-training an SDC and pedestrians with MAPPO yields 78% goal success and 14% collisions versus 35%/33% for rule-based baselines, with jaywalking causing 62% of collisions and evidence of poor anticipation via speed differentials.
citing papers explorer
-
Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage
CL-MARL uses an adaptive curriculum scheduler called FlexDiff and Counterfactual Group Relative Policy Advantage to break static-difficulty training in MARL and achieve higher win rates on hard StarCraft maps.
-
Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control
Proposes hierarchical MARL framework enforcing safety via constraint manifold at low level with theoretical guarantees and stationary dynamics for stable training and generalization.
-
Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning
Marope applies hierarchical MARL with decentralized lower-level rope policies and a centralized scheduler to achieve cooperative long rope skipping on Unitree G1 humanoids in simulation and reality.
-
SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication
SCALE-COMM uses contrastive alignment on latent embeddings to decouple and stabilize communication learning from policy optimization in decentralized MARL, showing gains on benchmarks and a warehouse task.
-
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
Co-training an SDC and pedestrians with MAPPO yields 78% goal success and 14% collisions versus 35%/33% for rule-based baselines, with jaywalking causing 62% of collisions and evidence of poor anticipation via speed differentials.