#
rllib
Here are 45 public repositories matching this topic...
PyBullet Gym environments for single and multi-agent reinforcement learning of quadcopter control
control
reinforcement-learning
uav
quadcopter
robotics
multi-agent
quadrotor
crazyflie
ros2
pybullet
gym-environment
rllib
-
Updated
Mar 5, 2022 - Python
-
Updated
Jan 28, 2022 - Python
A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.
lstm
quantitative-finance
ray
limit-order-book
quantitative-trading
financial-engineering
market-microstructure
zero-sum
high-frequency-trading
gym-environment
ppo
self-play
double-auction
multi-agent-reinforcement-learning
rllib
marl
n-player
zero-sum-games
-
Updated
Mar 11, 2022 - Jupyter Notebook
Deep Reinforcement Learning For Trading
python
machine-learning
reinforcement-learning
deep-learning
trading
keras
jupyter-notebook
quantitative-finance
algorithmic-trading
deep-q-network
quantitative-trading
keras-tensorflow
rllib
-
Updated
Feb 10, 2022 - Jupyter Notebook
An introductory tutorial about leveraging Ray core features for distributed patterns.
python
distributed-systems
scikit-learn
sharding
profiling
ray
futures
pattern-language
task-parallelism
actor-pattern
rllib
ray-tutorial
introductory-tutorial
-
Updated
Jan 3, 2022 - Jupyter Notebook
Walkthroughs for DSL, AirSim, the Vector Institute, and more
ubuntu
anaconda
tensorflow
slurm
tutorials
torch
nvidia
ray
unreal-engine-4
airsim
mujoco
rllib
robomaster-sdk
brax
robomaster-s1
dji-tello-talent
-
Updated
Jan 11, 2022 - C++
RLlib tutorials
-
Updated
Jan 2, 2022 - Jupyter Notebook
Adaptive real-time traffic light signal control system using Deep Multi-Agent Reinforcement Learning
-
Updated
Nov 17, 2020 - Python
0xangelo
commented
Sep 12, 2019
Currently we use a very ad-hoc procedure for scaling the quadratic component of NAF when used for exploration:
https://github.com/angelolovatto/raylab/blob/9820275b17ee085e1955a6d845c0bdf61333f8da/raylab/algorithms/naf/naf_policy.py#L150-L155
A possibly better alternative would be to scale it based on the desired average action stddev. Something like:
scale_tril * (1.0 / average_stDynamic multi-cell selection for cooperative multipoint (CoMP) using (multi-agent) deep reinforcement learning
python
mobile
reinforcement-learning
simulation
wireless
cellular
ray
comp
ppo
multi-agent-reinforcement-learning
rllib
cell-selection
-
Updated
Oct 8, 2021 - Python
An example implementation of an OpenAI Gym environment used for a Ray RLlib tutorial
-
Updated
Jan 2, 2022 - Python
Super Mario Bros training with Ray RLlib DQN algorithm
-
Updated
May 22, 2021 - Python
RL environment replicating the werewolf game to study emergent communication
python
reinforcement-learning
mafia-game
emergent-behavior
werewolf-game
rllib
emergent-communication
-
Updated
Mar 12, 2022 - Python
An open, minimalist Gym environment for autonomous coordination in wireless mobile networks.
python
environment
mobile
reinforcement-learning
simulation
optimization
management
evaluation
coordination
python3
gym
autonomous
wireless
cellular
mobile-networks
gym-environment
multi-agent-reinforcement-learning
rllib
stable-baselines
cell-selection
-
Updated
Feb 8, 2022 - Python
Training in bursts for defending against adversarial policies
reinforcement-learning
gym
ray
multiagent-reinforcement-learning
adversarial-examples
population-based-training
rllib
stable-baselines
tensorflow2
adversarial-policies
-
Updated
Dec 8, 2020 - Python
Used Flow, Ray/RLlib and OpenAI Gym to simulate and train autonomous vehicles/human drivers in SUMO (Simulation of Urban Mobility)
-
Updated
Dec 15, 2020 - Jupyter Notebook
My attempt to reproduce a water down version of PBT (Population based training) for MARL (Multi-agent reinforcement learning) using DDPPO (Decentralized & distributed proximal policy optimization) from ray[rllib].
ray
pbt
population-based-training
self-play
multi-agent-reinforcement-learning
rllib
marl
pbt-marl
ddppo
-
Updated
Aug 25, 2020 - Jupyter Notebook
ray project 中文文档
python
java
data-science
machine-learning
reinforcement-learning
deep-learning
optimization
parallel
distributed
model-selection
hyperparameter-optimization
ray
automl
hyperparameter-search
rllib
-
Updated
Sep 6, 2019 - Python
NIPS challenge 2018 Prosthetics playground and testing ideas
-
Updated
Jun 12, 2019 - Python
RL robust to deadlocks for the Flatland Challenge 2020.
-
Updated
Nov 27, 2020 - Jupyter Notebook
RL training for the 6DoF manipulator
-
Updated
Aug 11, 2020 - Python
reinforcement learning alogrithm implement with Ray
-
Updated
Sep 10, 2021 - Python
An autonomous driving simulator for modelling Vehicle to Infrastructure (V2I) conditions.
reinforcement-learning
newtonian-mechanics
policy-gradient
autonomous-driving
autonomous-vehicles
pygame-application
v2i
gym-environment
ppo
intelligent-driver-model
rllib
-
Updated
Oct 12, 2021 - Jupyter Notebook
An open source reinforcement learning platform built using Ray's RLlib and Tune that simplifies the setup for hyperparameter optimization and model training against OpenAI Gym environments.
python
java
data-science
machine-learning
reinforcement-learning
deep-learning
openai-gym
openai
hyperparameter-optimization
ray
automl
rllib
-
Updated
Dec 31, 2021 - Python
A reinforcement learning environment inspired by Among Us
-
Updated
Mar 10, 2022 - Python
Urban mobility simulations with Python3, RLlib (Deep Reinforcement Learning) and Mesa (Agent-based modeling)
-
Updated
Feb 10, 2022 - Jupyter Notebook
Improve this page
Add a description, image, and links to the rllib topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the rllib topic, visit your repo's landing page and select "manage topics."
Search before asking
Ray Component
Ray Clusters
What happened + What you expected to happen
I was trying to launch a Ray cluster on GCP via my macOS. When I disabled the
dockerfield and used thesetup_commandsfield to set up the new node, everything went well. However, when