🕷️
SetupAI
繁

Search

Few direct matches — filled in with the latest updates.

Tag: #offline-rl3 results

PIER RL Cuts Shipping Fuel Waste 9-Fold

PIER RL Cuts Shipping Fuel Waste 9-Fold

PIER is a physics-informed offline RL framework that learns fuel-efficient, safety-aware maritime routing from historical AIS data and ocean reanalysis, without needing online simulators or forecasts. It reduces mean CO2 emissions by 10% versus great-circle routing and slashes catastrophic fuel waste from 4.8% to 0.5% of voyages on 2023 Gulf of Mexico routes. The method shows 3.5x lower fuel variance and transfers to other domains like wildfire evacuation.

ArXiv AIResearch•Mar 19#offline-rl#physics-informed#maritime-routing
COffeE-PSRO for Offline Multiagent RL

COffeE-PSRO for Offline Multiagent RL

COffeE-PSRO extends PSRO for offline multiagent games by quantifying dynamics uncertainty and applying conservatism from offline RL to favor low-regret equilibria. It introduces a meta-strategy solver for offline exploration. Experiments show it extracts lower-regret solutions than state-of-the-art offline methods.

ArXiv AIResearch•Mar 3#multiagent-rl#offline-rl#game-theory
DMEMM Enhances Offline RL Planning

DMEMM Enhances Offline RL Planning

DMEMM is a novel diffusion-based planning method for offline reinforcement learning that modulates training by incorporating environment transition dynamics and reward functions. It ensures trajectory consistency with real environments, addressing limitations in conventional diffusion models. Experiments demonstrate state-of-the-art performance.

ArXiv AIResearch•Feb 25#diffusion-planning#offline-rl