synapse-rl

Synapse RL: A PyTorch Framework for Reinforcement Learning

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 3 DOI reference(s) in README
✓
Academic publication links
Links to: zenodo.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (9.9%) to scientific vocabulary

Keywords

ddpg deep-deterministic-policy-gradient deep-reinforcement-learning framework pytorch reinforcement-learning sac soft-actor-critic

Last synced: 4 months ago · JSON representation ·

Repository

Synapse RL: A PyTorch Framework for Reinforcement Learning

Basic Info

Host: GitHub
Owner: arbit3rr
License: apache-2.0
Language: Jupyter Notebook
Default Branch: main
Homepage:
Size: 20.1 MB

Statistics

Stars: 9
Watchers: 1
Forks: 1
Open Issues: 0
Releases: 1

Topics

ddpg deep-deterministic-policy-gradient deep-reinforcement-learning framework pytorch reinforcement-learning sac soft-actor-critic

Created about 3 years ago · Last pushed 4 months ago

Metadata Files

Readme License Citation

Synapse Reinforcement Learning

Synapse is a framework for implementing Reinforcement Learning (RL) algorithms in PyTorch. The repository includes popular algorithms such as Deep Q-Networks, Policy Gradients, and Actor-Critic, as well as others.

One of the advantages of using Synapse-RL is its compatibility with gym-based environments. Gym provides a standard interface for working with environments to benchmark RL models. Synapse-RL also includes various utility functions and classes that make it easy to experiment with different hyperparameters, test different training approaches, and visualize training results.

Colab

Supported Algorithms

| RL Algorithm | Description | | --- | --- | | Deep Q Learning | Discrete | | Policy Gradient | Discrete | | Actor Critic (A2C) | Discrete | | Deep Deterministic Policy Gradient (DDGP) | Continuous | | Soft Actor Critic (SAC) | Continuous | | Proximal Policy Optimization (PPO) | Continuous |

Tensorboard

Synapse now supports tensorboard. bash tensorboard --logdir ./

Inference

```python import gymnasium as gym from syn_rl import SAC

Initialize the Pendulum/MountainCar environment and agent

env = gym.make('Pendulum-v1', g=9.81) statesize = env.observationspace.shape[0] actionsize = env.actionspace.shape[0] agent = SAC(statesize, actionsize, actionrange=[env.actionspace.low, env.actionspace.high], hiddendim=[128]) result = agent.train(env, episodes=500) ```

Citation

Owner

Name: Amirhossein Heydarian Ardakani
Login: arbit3rr
Kind: user

Website: https://scholar.google.com/citations?user=5U9fGhYAAAAJ&hl=en
Repositories: 13
Profile: https://github.com/arbit3rr

Citation (CITATION.cff)

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: Synapse RL
message: PyTorch framework for reinforcement learning
type: software
authors:
  - given-names: Amirhossein
    family-names: Heydarian Ardakani
    email: amirhossein261077@live.com
identifiers:
  - type: doi
    value: 10.5281/zenodo.8009955
repository-code: 'https://github.com/amirhosseinh77/Synapse-RL'
date-released: '2022-11-22'

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science