D4RL supplies new offline RL benchmarks and datasets from expert and mixed sources to expose weaknesses in existing algorithms and standardize evaluation.
Deep imitative mod- els for flexible inference, planning, and control
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
NeuroTrajectory is a neuroevolutionary method that trains deep neural networks via genetic algorithms to estimate multi-objective optimal state trajectories over a finite horizon for autonomous vehicle motion planning.
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
citing papers explorer
-
NeuroTrajectory: A Neuroevolutionary Approach to Local State Trajectory Learning for Autonomous Vehicles
NeuroTrajectory is a neuroevolutionary method that trains deep neural networks via genetic algorithms to estimate multi-objective optimal state trajectories over a finite horizon for autonomous vehicle motion planning.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.