DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning.
Longxiang HeLinrui ZhangJunbo TanXueqian WangPublished in: CoRR (2023)
Keyphrases
- policy search
- reinforcement learning
- model free
- reinforcement learning algorithms
- continuous state
- dynamic programming
- continuous action
- function approximation
- temporal difference
- optimal policy
- state space
- markov decision problems
- policy gradient
- markov decision processes
- partially observable markov decision processes
- reward function
- policy iteration
- function approximators
- control policies
- multi agent
- learning algorithm