gold

package module

v0.0.0-...-225e849 Latest Latest Go to latest Published: Oct 22, 2020 License: Apache-2.0 Imports: 0 Imported by: 0

Details

Valid go.mod file

The Go module system was introduced in Go 1.11 and is the official dependency management solution for Go.
Redistributable license

Redistributable licenses place minimal restrictions on how software can be used, modified, and redistributed.
Tagged version

Modules with tagged versions give importers more predictable builds.
Stable version

When a project reaches major version v1 it is considered stable.
Learn more about best practices

Repository

github.com/aunum/gold

Links

Open Source Insights

README ¶

cartpole

Overview

Gold is a reinforcement learning library for Go. It provides a set of agents that can be used to solve challenges in various environments. The library further contains a composable tooling for creating agents and visualizing their performance.

Quick Start

go run ./pkg/v1/agent/deepq/experiments/cartpole/main.go

Requirements

Go >= v13.0
Docker
A browser that isn't IE

Agents

All of the agent implementations can be found in pkg/v1/agent each agent has an experiments folder providing demos across various environments.

agent	algorithm
pkg/v1/agent/q	Q Learning
pkg/v1/agent/deepq	Deep Q learning with Double Q
pkg/v1/agent/reinforce	REINFORCE aka Monte Carlo Policy Gradients
pkg/v1/agent/nes	Natural Evolution Strategies
pkg/v1/agent/her	Hindsight Experience Replay
pkg/v1/agent/ppo	Proximal Policy Optimization ⚠️ in progress

Docs

Each package contains a README explaining the usage, also see GoDoc.

Contributing

Please open an MR for any issues or feature requests.

The project is fairly simple to hack on, environments are provided through Sphere, models are provided through Goro.

Feel free to ping @pbarker on Gopher slack.

Roadmap

More agents, more environments; see Future Thoughts
Accelerated compute support
Tuning libraries
Deployments

Inspiration

OpenAI Baselines
The Gorgonia Project
Gonum
RL Overview by Lilian Weng
Open Endedness by Kenneth O. Stanley, Joel Lehman and Lisa Soros
AI-GAs by Jeff Clune
The Bitter Lesson by Rich Sutton
Reinforcement Learning: An Introduction by Rich Sutton and Andrew Barto

Documentation ¶

Overview ¶

Package gold provides reinforcement learning libraries and agent implementations.

Source Files ¶

View all Source files

doc.go

Directories ¶

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL

Path	Synopsis
pkg
v1/agent Package agent provides the agent implementations and base tooling.	Package agent provides the agent implementations and base tooling.
v1/agent/deepq Package deepq is an agent implementation of the DeepQ algorithm.	Package deepq is an agent implementation of the DeepQ algorithm.
v1/agent/deepq/experiments/cartpole
v1/agent/deepq/experiments/pong
v1/agent/her Package her is an agent implementation of the Hindsight Experience Replay algorithm.	Package her is an agent implementation of the Hindsight Experience Replay algorithm.
v1/agent/her/experiments/bitflip
v1/agent/nes Package nes is an agent implementation of the Natural Evolution Strategies algorithm.	Package nes is an agent implementation of the Natural Evolution Strategies algorithm.
v1/agent/nes/experiments/cartpole
v1/agent/ppo Package ppo is an agent implementation of the Proximal Policy Optimization algorithm.	Package ppo is an agent implementation of the Proximal Policy Optimization algorithm.
v1/agent/ppo/experiments/cartpole
v1/agent/q Package q is an agent implementation of the Q learning algorithm.	Package q is an agent implementation of the Q learning algorithm.
v1/agent/q/experiments/taxi
v1/agent/reinforce Package reinforce is an agent implementation of the REINFORCE algorithm.	Package reinforce is an agent implementation of the REINFORCE algorithm.
v1/agent/reinforce/experiments/cartpole
v1/common Package common provides common methods and tooling for the agents.	Package common provides common methods and tooling for the agents.
v1/common/num Package num provides various numeric functions.	Package num provides various numeric functions.
v1/common/op Package op provides extended Gorgonia graph operations.	Package op provides extended Gorgonia graph operations.
v1/common/require Package require provides methods for enforcing requirements on values or exiting.	Package require provides methods for enforcing requirements on values or exiting.
v1/dense Package dense provides methods for Gorgonia's Dense Tensors.	Package dense provides methods for Gorgonia's Dense Tensors.
v1/env Package env provides a wrapper for interacting with Sphere as well as normalization tools.	Package env provides a wrapper for interacting with Sphere as well as normalization tools.
v1/track Package track provides tooling for tracking agent metrics.	Package track provides tooling for tracking agent metrics.
v1/ui Package ui package contains resources for creating agent dashboards.	Package ui package contains resources for creating agent dashboards.
v1/ui/sse Package sse provides server sent events to the agent dashboard.	Package sse provides server sent events to the agent dashboard.