acme
selfhosted-apps-docker
Our great sponsors
acme | selfhosted-apps-docker | |
---|---|---|
11 | 150 | |
3,373 | 1,427 | |
1.4% | - | |
6.0 | 8.8 | |
2 days ago | 7 days ago | |
Python | Shell | |
Apache License 2.0 | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
acme
-
Fast and hackable frameworks for RL research
I'm tired of having my 200m frames of Atari take 5 days to run with dopamine, so I'm looking for another framework to use. I haven't been able to find one that's fast and hackable, preferably distributed or with vectorized environments. Anybody have suggestions? seed-rl seems promising but is archived (and in TF2). sample-factory seems super fast but to the best of my knowledge doesn't work with replay buffers. I've been trying to get acme working but documentation is sparse and many of the features are broken.
-
How much of a MuJoCo simulation or real life robot can you train on a 3090?
I'm training a few algorithms from Deepmind's acme library on some MuJoCo models and I'm wondering how long this will take to train and what it's going to do to my electric bill. Is a 3090 or two enough to train something to keep its balance, or do a task, or do I need to wait for the 8090 to come out?
-
Recomendations of framework/library for MARL
Recently dm-acme also added support for multi-agent environments. Acme: https://github.com/deepmind/acme
- Have you used any good DRL library?
- Is there a way to get PPO controlled agents to move a little more gracefully?
-
Worthwhile to convert custom env to be dm_env compatible?
Can anyone speak to their experience using acme (https://github.com/deepmind/acme) and by extension dm_env (https://github.com/deepmind/dm_env)? I'm wondering if it would be worthwhile for me to invest the time into converting my custom environment (which loosely follows the standard RL setup) over to this format.
-
[D] Physics and Reinforcement Learning - Discussion of Deepmind's work
acme/acme/agents/tf/mpo at master · deepmind/acme · GitHub
- Applied resources in Pytorch?
-
deepmind acme compatible with windows?
after installing it in a clean env, I tried to run the example provided for solving the gym cartpole env: https://github.com/deepmind/acme/blob/master/examples/control/run_d4pg_gym.py
-
Spec for RL agent implementation?
Acme has a slightly different one: https://github.com/deepmind/acme which includes specs for agents, buffers etc. It is very general. You can see their component description here: https://github.com/deepmind/acme/blob/master/docs/components.md
selfhosted-apps-docker
-
Minecraft server
Heres documentation how I run mine. You need to learn a bit of docker, but its easy.
-
Rustdesk very poor performance with own server
Heres the way I deployed it in docker using S6 image. Maybe try that if theres a change.
-
RustDesk - Self Hosted Setup Guide
WD=/opt/rustdesk #rm $WD/ -R mkdir -p $WD/{setup,data,web} cd $WD/setup cat << 'EOF' >docker-compose.yaml version: '3.7' #Links #https://hub.docker.com/r/rustdesk/rustdesk-server/tags #https://rustdesk.com/docs/en/self-host/rustdesk-server-oss/docker/ #https://github.com/DoTheEvo/selfhosted-apps-docker/tree/master/rustdesk #https://github.com/rustdesk/rustdesk-server#s6-overlay-based-images #https://rustdesk.com/docs/en/self-host/rustdesk-server-pro/relay/ #https://rustdesk.com/docs/en/dev/build/web/ services: rustdesk_server: container_name: rustdesk_server hostname: rustdesk_server image: ${SERVER_IMAGE} # network_mode: host networks: - rustdesk_net ports: - 21115:21115 - 21116:21116 - 21116:21116/udp - 21117:21117 - 21118:21118 - 21119:21119 volumes: - type: bind source: /opt/rustdesk/data/ target: /data environment: - 'TZ=${TZ}' - 'RELAY=${RELAY}' - 'ENCRYPTED_ONLY=${ENCRYPTED_ONLY}' - 'KEY_PUB=${KEY_PUB}' - 'KEY_PRIV=${KEY_PRIV}' rustdesk_web: container_name: rustdesk_web hostname: rustdesk_web image: pmietlicki/rustdesk-web-client:latest # network_mode: host networks: - rustdesk_net ports: - 5000:5000 volumes: #docker cp rustdesk_web:/app . #sed -i -e 's/supportdesk.itportaal.nl/sub.domain.com/g' ./app/build/web/main.dart.js #sed -i -e 's/OvYPJS8I5xV+d6sx3a7Ce9TVakfKdT3Zy3T7C1jjx+A=/PUBKEY/g' ./app/build/web/main.dart.js - type: bind source: /opt/rustdesk/web/app/ target: /app - type: bind source: /opt/rustdesk/data/ target: /root environment: - 'TZ=${TZ}' networks: rustdesk_net: driver: bridge EOF
-
Reverse Proxy or Not ?
I tested several reverse proxy setups, the one I like the best is Caddy for its simplicity while being very feature rich. Here is a guide with examples how to setup Caddy. It includes even monitoring who connects from where.
-
Looking for the best VPN container for Docker
I used plain wireguard on dockerhost for a while, now I am running wg-easy.
-
Best reverse proxy approach? (Cloudflare, Tailscale, NextDNS, Oracle Cloud, Caddy)
This guide could be useful.
-
What monitoring software is popular amongst sysadmins? Networking Disk Uptime Bandwidth
Here is some basic setup to get the idea.
-
I don't know what distro should I use and my other questions
This repo should generally be useful, there is speedrun to hosting shit in docker in it...
-
[HELP] Can you help me with this docker compose file (example)?
This is bookstack compose I use.
-
Looking for easy to set up and use tool for maintaining/monitoring handful of ubuntu machines updates
prometheus + grafana + loki for monitoring, this could help
What are some alternatives?
dm_env - A Python interface for reinforcement learning environments
mistborn
Mava - 🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
EteSync Server - The Etebase server (so you can run your own)
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
docker-swag - Nginx webserver and reverse proxy with php support and a built-in Certbot (Let's Encrypt) client. It also contains fail2ban for intrusion prevention.
MPO - Pytorch implementation of "Maximum a Posteriori Policy Optimization" with Retrace for Discrete gym environments
Whisparr
tonic - Tonic RL library
Traefik-v2-examples - Traefik v2 guide by examples
gym - A toolkit for developing and comparing reinforcement learning algorithms.
DockSTARTer - DockSTARTer helps you get started with running apps in Docker.