Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning.
Cheng LuHuayu ChenJianfei ChenHang SuChongxuan LiJun ZhuPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- energy consumption
- prediction accuracy
- real time
- low energy
- random sampling
- energy minimization
- total energy
- state space
- dynamic programming
- energy function
- sample size
- mobile robot
- monte carlo
- prediction model
- function approximation
- artificial neural networks
- energy efficiency
- sampling algorithm
- prediction algorithm
- social networks
- data sets