Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/amazon-science/fast-rl-with-slow-updates

https://github.com/amazon-science/fast-rl-with-slow-updates

Science Score: 26.0%

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

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.1%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: amazon-science
  • License: apache-2.0
  • Language: Jupyter Notebook
  • Default Branch: master
  • Size: 2.14 MB
Statistics
  • Stars: 18
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed almost 3 years ago
Metadata Files
Readme License

README.md

Fast RL with Slow Updates

Introduction

This is the official repository for our paper "Faster deep reinforcement learning with slower online network", which we presented at NeurIPS 2022. We built on the Dopamine, which is a research framework for fast prototyping of reinforcement learning algorithms.

We make minimal changes to the standard DQN and Rainbow algorithms. Please see ./dopamine/agents/dqn/dqn_agent.py. Argument mu is defined to activate our Proximal Iteration. If `mu > 0.0', then Proximal Iteration is being used, and otherwise the model is trained without it, meaning we are implementing regular DQN/Rainbow.

Prerequisites

Dopamine supports Atari environments and Mujoco environments. Install the environments you intend to use before you install Dopamine:

Atari

  1. Install the atari roms following the instructions from atari-py.
  2. pip install ale-py (we recommend using a virtual environment):
  3. unzip $ROM_DIR/ROMS.zip -d $ROM_DIR && ale-import-roms $ROM_DIR/ROMS (replace $ROM_DIR with the directory you extracted the ROMs to).

Installing from Source

The most common way to use Dopamine is to install it from source and modify the source code directly:

git clone https://github.com/google/dopamine

After cloning, install dependencies:

pip install -r dopamine/requirements.txt

Dopamine supports tensorflow (legacy) and jax (actively maintained) agents. View the Tensorflow documentation for more information on installing tensorflow.

Note: We recommend using a virtual environment when working with Dopamine.

Installing with Pip

Note: We strongly recommend installing from source for most users.

Installing with pip is simple, but Dopamine is designed to be modified directly. We recommend installing from source for writing your own experiments.

pip install dopamine-rl

Running tests

You can test whether the installation was successful by running the following from the dopamine root directory.

export PYTHONPATH=$PYTHONPATH:$PWD python -m tests.dopamine.atari_init_test

Owner

  • Name: Amazon Science
  • Login: amazon-science
  • Kind: organization

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Issues and Pull Requests

Last synced: over 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

docker/atari/Dockerfile docker
  • ${base_image} latest build
docker/core/Dockerfile docker
  • nvidia/cuda ${cuda_docker_tag} build
docker/mujoco/Dockerfile docker
  • ${base_image} latest build
dopamine/labs/tandem_dqn/requirements.txt pypi
  • absl-py *
  • atari-py *
  • dopamine-rl *
  • gin-config *
  • gym *
  • numpy *
  • tensorflow *
requirements.txt pypi
  • Keras-Preprocessing >=1.1.2
  • Markdown >=3.2.2
  • Pillow >=7.2.0
  • Werkzeug >=1.0.1
  • absl-py >=0.9.0
  • astunparse >=1.6.3
  • atari-py >=0.2.6
  • cachetools >=4.1.1
  • certifi >=2020.6.20
  • chardet >=3.0.4
  • cloudpickle >=1.3.0
  • cycler >=0.10.0
  • flax >=0.3.3
  • future >=0.18.2
  • gast >=0.3.3
  • gin-config >=0.3.0
  • google-auth >=1.19.2
  • google-auth-oauthlib >=0.4.1
  • google-pasta >=0.2.0
  • grpcio >=1.30.0
  • gym >=0.17.2
  • h5py >=2.10.0
  • idna >=2.10
  • jax >=0.2.12
  • jaxlib >=0.1.65
  • kiwisolver >=1.2.0
  • matplotlib >=3.3.0
  • msgpack >=1.0.0
  • numpy >=1.18.5
  • oauthlib >=3.1.0
  • opencv-python >=4.3.0.36
  • opt-einsum >=3.3.0
  • pandas >=1.0.5
  • protobuf >=3.12.2
  • pyasn1 >=0.4.8
  • pyasn1-modules >=0.2.8
  • pygame >=1.9.6
  • pyglet >=1.5.0
  • pyparsing >=2.4.7
  • python-dateutil >=2.8.1
  • pytz >=2020.1
  • requests >=2.24.0
  • requests-oauthlib >=1.3.0
  • rsa >=4.6
  • scipy >=1.4.1
  • setuptools >=49.2.01
  • six >=1.15.0
  • tensorboard *
  • tensorboard-plugin-wit *
  • tensorflow *
  • tensorflow-estimator *
  • tensorflow-probability >=0.13.0
  • termcolor >=1.1.0
  • tf-slim >=1.1.0
  • urllib3 >=1.25.10
  • wrapt >=1.12.1
setup.py pypi
  • absl-py *
  • gin-config *
  • gym *
  • opencv-python *
  • tensorflow *