Open-source Reinforcement Learning Model sac - Hopper - v3: Free Deployment for Robot Jumping Motion Control

Sac Hopper V3

Developed by sb3

This is a reinforcement learning model based on the SAC algorithm, designed to control robot hopping movements in the Hopper-v3 environment.

Physics Model #Continuous Action Control #Deep Reinforcement Learning #Robot Motion Control

Downloads 44

Release Time : 6/2/2022

Model Overview

The model is trained using the Soft Actor-Critic (SAC) algorithm, specifically designed to solve continuous control tasks in the Hopper-v3 environment.

Model Features

Based on SAC Algorithm

Uses the Soft Actor-Critic algorithm, suitable for handling reinforcement learning problems in continuous action spaces.

Stable Training

Implemented via stable-baselines3, providing a reliable training process.

High Performance

Achieves an average reward of 2266.78 in the Hopper-v3 environment.

Model Capabilities

Continuous Action Control

Robot Motion Control

Reinforcement Learning Task Solving

Use Cases

Robot Control

Hopper Robot Jump Control

Controls the jumping movements of a simulated Hopper robot.

Average reward 2266.78 +/- 1121.81

Reinforcement Learning Research

Continuous Control Benchmarking

Can serve as a benchmark model for continuous control tasks.

Property	Details
Library Name	stable-baselines3
Tags	Hopper-v3, deep-reinforcement-learning, reinforcement-learning, stable-baselines3
Model Name	SAC
Mean Reward	2266.78 +/- 1121.81
Task Type	reinforcement-learning
Dataset	Hopper-v3