Diffusion Actor-Critic with Entropy Regulator

arXiv:2405.15177v1 Announce Type: new
Abstract: Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution with learned mean and variance, which constrains their capability to acquire complex policies. In response to this problem, we propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER). This algorithm conceptualizes the reverse process of the diffusion model as a novel policy …

abstract actor actor-critic algorithms arxiv capability control cs.ai cs.lg decision diffusion distribution entropy however making mean policies policy problem regulator reinforcement reinforcement learning tasks type variance