The D2AC algorithm shows improved learning stability in reinforcement learning tasks, highlighting advances in distributional RL and policy optimization.
We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy gradients and the complexity of backpropagation through time. This stable learning process is critically enabled by our second contribution: a robust distributional critic, which we design through a fusion of distributional RL and clipped double Q-learning. The resulting algorithm is highly effective, achieving state-of-the-art performance on a benchmark of eighteen hard RL tasks, including Humanoid, Dog, and Shadow Hand domains, spanning both dense-reward and goal-conditioned RL scenarios. Beyond standard benchmarks, we also evaluate a biologically motivated predator-prey task to examine the behavioral robustness and generalization capacity of our approach.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: