paper-with-me

Papers

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

2024-03-01 · Michal Nauman, Michał Bortkiewicz, Piotr Miłoś, Tomasz Trzciński, Mateusz Ostaszewski, Marek Cygan

Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional agents. However, many of these techniques have been tested in limited settings, often on tasks from single simulation benchmarks and against well-known algorithms rather than a range of regularization approaches. This limits our understanding of the specific mechanisms driving RL improvements. To address this, we implemented over 60 different off-policy agents, each integrating established regularization techniques from recent state-of-the-art algorithms. We tested these agents across 14 diverse tasks from 2 simulation benchmarks, measuring training metrics related to overestimation, overfitting, and plasticity loss -- issues that motivate the examined regularization techniques. Our findings reveal that while the effectiveness of a specific regularization setup varies with the task, certain combinations consistently demonstrate robust and superior performance. Notably, a simple Soft Actor-Critic agent, appropriately regularized, reliably finds a better-performing policy within the training regime, which previously was achieved mainly through model-based approaches.

📄 PDF Abstract BibTeX arXiv:2403.00514

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Addressing Function Approximation Error in Actor-Critic Methods

2018-02-26 · ICML 2018 7 · Scott Fujimoto, Herke van Hoof, David Meger

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an ac…

Continuous ControlOpenAI GymQ-Learningreinforcement-learning+2

Deep Reinforcement Learning With Adaptive Combined Critics

2021-01-01 · Huihui Zhang, Wu Huang

The overestimation problem has long been popular in deep value learning, because function approximation errors may lead to amplified value estimates and suboptimal policies. There have been several methods to deal with t…

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+2

Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss

2025-04-14 · Ukjo Hwang, SongNam Hong

Overestimation is a fundamental characteristic of model-free reinforcement learning (MF-RL), arising from the principles of temporal difference learning and the approximation of the Q-function. To address this challenge,…

Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors

2020-01-09 · Jingliang Duan, Yang Guan, Shengbo Eben Li, Yangang Ren 외

In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSA…

continuous-controlContinuous ControlMuJoCoreinforcement-learning+2

SQT -- std $Q$-target

2024-02-03 · Nitsan Soffair, Dotan Di-Castro, Orly Avner, Shie Mannor

Std $Q$-target is a conservative, actor-critic, ensemble, $Q$-learning-based algorithm, which is based on a single key $Q$-formula: $Q$-networks standard deviation, which is an "uncertainty penalty", and, serves as a min…

MuJoCoQ-Learning