paper-with-me

홈 › Papers

Evolutionary Stochastic Policy Distillation

2020-04-27 · Hao Sun, Xinyu Pan, Bo Dai, Dahua Lin, Bolei Zhou

Solving the Goal-Conditioned Reward Sparse (GCRS) task is a challenging reinforcement learning problem due to the sparsity of reward signals. In this work, we propose a new formulation of GCRS tasks from the perspective of the drifted random walk on the state space, and design a novel method called Evolutionary Stochastic Policy Distillation (ESPD) to solve them based on the insight of reducing the First Hitting Time of the stochastic process. As a self-imitate approach, ESPD enables a target policy to learn from a series of its stochastic variants through the technique of policy distillation (PD). The learning mechanism of ESPD can be considered as an Evolution Strategy (ES) that applies perturbations upon policy directly on the action space, with a SELECT function to check the superiority of stochastic variants and then use PD to update the policy. The experiments based on the MuJoCo robotics control suite show the high learning efficiency of the proposed method.

📄 PDF Abstract BibTeX arXiv:2004.12909

Code (1)

decisionforce/ESPD 공식 구현 pytorch

Tasks

MuJoCoReinforcement Learning

Similar Papers 제목 키워드 기반

Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts

2024-10-22 · Sheryl Paul, Jyotirmoy V. Deshmukh

Reinforcement learning (RL) has been successfully applied to solve the problem of finding obstacle-free paths for autonomous agents operating in stochastic and uncertain environments. However, when the underlying stochas…

Reinforcement Learning (RL)

Evolving Constrained Reinforcement Learning Policy

2023-04-19 · Chengpeng Hu, Jiyuan Pei, Jialin Liu, Xin Yao

Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improve…

Evolutionary Algorithmsreinforcement-learningReinforcement Learning

A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning

2022-02-21 · Youssef Diouane, Aurelien Lucchi, Vihang Patil

Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function…

Evolutionary Systems Thinking -- From Equilibrium Models to Open-Ended Adaptive Dynamics

2026-02-17 · Dan Adler arxiv

Complex change is often described as "evolutionary" in economics, policy, and technology, yet most system dynamics models remain constrained to fixed state spaces and equilibrium-seeking behavior. This paper argues that …

SPARK: Spatial Policy-driven Adaptive Reinforcement learning for Knowledge distillation

2026-06-13 · Mohamed Jismy Aashik Rasool, Shabir Ahmad, Gisong Oh, Teag Kuen Whangbo arxiv

Low-bit quantization enables deployment of image restoration (IR) networks on resource-constrained devices, but introduces rounding noise that disproportionately degrades high-frequency regions such as edges and fine tex…

Reinforcement LearningKnowledge DistillationImage Restoration