English
Related papers

Related papers: Actor Loss of Soft Actor Critic Explained

200 papers

Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value…

Machine Learning · Statistics 2017-03-14 Yemi Okesanjo , Victor Kofia

A model, based on Gribov's Reggeon calculus, is proposed and applied to processes of soft diffraction at high energies. It is shown that by accounting for absorptive corrections for all legs of triple-Regge and loop diagrams a good…

High Energy Physics - Phenomenology · Physics 2009-09-29 A. B. Kaidalov , M. G. Poghosyan

Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-based RL algorithms typically causes immediate drops in performance. We provide evidence consistent…

Machine Learning · Computer Science 2026-03-02 Nathan Samuel de Lara , Florian Shkurti

A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to…

Machine Learning · Computer Science 2023-04-17 Eric Graves , Ehsan Imani , Raksha Kumaraswamy , Martha White

The Soft Actor-Critic (SAC) algorithm, a state-of-the-art method in maximum entropy reinforcement learning, traditionally relies on minimizing reverse Kullback-Leibler (KL) divergence for policy updates. However, this approach leads to an…

Machine Learning · Computer Science 2025-06-03 Yixian Zhang , Huaze Tang , Changxu Wei , Wenbo Ding

Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and…

Machine Learning · Computer Science 2018-08-10 Tuomas Haarnoja , Aurick Zhou , Pieter Abbeel , Sergey Levine

This paper proposes a new actor-critic-style algorithm called Dual Actor-Critic or Dual-AC. It is derived in a principled way from the Lagrangian dual form of the Bellman optimality equation, which can be viewed as a two-player game between…

Machine Learning · Computer Science 2018-01-01 Bo Dai , Albert Shaw , Niao He , Lihong Li , Le Song

Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work…

Machine Learning · Statistics 2025-05-07 Kevin Tan , Wei Fan , Yuting Wei

Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which…

Robotics · Computer Science 2017-10-19 Lerrel Pinto , Marcin Andrychowicz , Peter Welinder , Wojciech Zaremba , Pieter Abbeel

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still outstanding. Working…

Machine Learning · Statistics 2021-03-02 Max B. Paulus , Dami Choi , Daniel Tarlow , Andreas Krause , Chris J. Maddison

Variational inference using the reparameterization trick has enabled large-scale approximate Bayesian inference in complex probabilistic models, leveraging stochastic optimization to sidestep intractable expectations. The reparameterization…

Machine Learning · Statistics 2020-02-13 Christian A. Naesseth , Francisco J. R. Ruiz , Scott W. Linderman , David M. Blei

We introduce a sequence-conditioned critic for Soft Actor--Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets. Unlike prior approaches that (i) score state--action pairs in…

Machine Learning · Computer Science 2025-09-30 Dong Tian , Onur Celik , Gerhard Neumann

The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in…

Artificial Intelligence · Computer Science 2019-06-13 Elita Lobo , Scott Jordan

The reparameterization trick is widely used in variational inference as it yields more accurate estimates of the gradient of the variational objective than alternative approaches such as the score function method. Although there is…

Machine Learning · Statistics 2018-12-31 Ming Xu , Matias Quiroz , Robert Kohn , Scott A. Sisson

Existing imitation learning methods mainly focus on making an agent effectively mimic a demonstrated behavior, but do not address the potential contradiction between the behavior style and the objective of a task. There is a general lack of…

Machine Learning · Computer Science 2022-09-28 Mingxi Tan , Andong Tian , Ludovic Denoyer

We address the issue of estimation bias in deep reinforcement learning (DRL) by introducing solution mechanisms that include a new, twin TD-regularized actor-critic (TDR) method. It aims at reducing both over and under-estimation errors.…

Machine Learning · Computer Science 2023-11-08 Junmin Zhong , Ruofan Wu , Jennie Si

In this paper, we propose a second-order deterministic actor-critic framework in reinforcement learning that extends the classical deterministic policy gradient method to exploit curvature information of the performance function. Building…

Machine Learning · Computer Science 2025-11-13 Arash Bahari Kordabad , Dean Brandner , Sebastien Gros , Sergio Lucia , Sadegh Soudjani

Quantum computing has a superior advantage in tackling specific problems, such as integer factorization and Simon's problem. For more general tasks in machine learning, by applying variational quantum circuits, more and more quantum…

Quantum Physics · Physics 2021-12-23 Qingfeng Lan

Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance…

Artificial Intelligence · Computer Science 2017-04-18 Marochko Vladimir , Leonard Johard , Manuel Mazzara

Many popular practical reinforcement learning (RL) algorithms employ evolving reward functions-through techniques such as reward shaping, entropy regularization, or curriculum learning-yet their theoretical foundations remain…

Machine Learning · Computer Science 2025-10-15 Rui Hu , Yu Chen , Longbo Huang