policy

Solving-Inverted-Pendulum-Environment-using-Soft-Actor-Critic-Reinforcement-Learning-

sankalpkalode49 · PyTorch

or hover any field below to flag it

Overview

Name
Solving-Inverted-Pendulum-Environment-using-Soft-Actor-Critic-Reinforcement-Learning-
Author
sankalpkalode49
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Train a reinforcement learning agent to balance an inverted pendulum using the Soft Actor-Critic (SAC) algorithm. This repository contains a full PyTorch implementation from scratch, complete with custom actor-critic networks, experience replay, and visualization.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

0+20 mentioned but not in catalog yet

No robots list Solving-Inverted-Pendulum-Environment-using-Soft-Actor-Critic-Reinforcement-Learning- as compatible yet. Know of one? Flag it above.

Compatible environments

0

No environments list Solving-Inverted-Pendulum-Environment-using-Soft-Actor-Critic-Reinforcement-Learning- yet.

Datasets that reference this policy

0

No datasets reference Solving-Inverted-Pendulum-Environment-using-Soft-Actor-Critic-Reinforcement-Learning- yet.