Papers › Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients

Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients

8 Sep 2024arXiv:2409.04971archive 2025-07-28

Luca Della Libera

Recent advances in deep reinforcement learning have achieved impressive results in a wide range of complex tasks, but poor sample efficiency remains a major obstacle to real-world deployment. Soft actor-critic (SAC) mitigates this problem by combining stochastic policy optimization and off-policy learning, but its applicability is restricted to distributions whose gradients can be computed through the reparameterization trick. This limitation excludes several important examples such as the beta distribution, which was shown to improve the convergence rate of actor-critic algorithms in high-dimensional continuous control problems thanks to its bounded support. To address this issue, we investigate the use of implicit reparameterization, a powerful technique that extends the class of reparameterizable distributions. In particular, we use implicit reparameterization gradients to train SAC with the beta policy on simulated robot locomotion environments and compare its performance with common baselines. Experimental results show that the beta policy is a viable alternative, as it outperforms the normal policy and is on par with the squashed normal policy, which is the go-to choice for SAC. The code is available at https://github.com/lucadellalib/sac-beta.

PaperPDFCode

Code

lucadellalib/sac-beta officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Continuous ControlDeep Reinforcement Learningcontinuous-control

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingConvolutionDilated ConvolutionGlobal Average PoolingSAC

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections