Build software better, together

ray-project / ray

Star

Open

[RLlib] Policy weights overwritten in self-play for local_mode

george-skal commented Jun 28, 2021

Hi all!
I am trying a self-play based scheme, where I want to have two agents in waterworld environment have a policy that is being trained (“shared_policy_1”) and other 3 agents that sample a policy from a menagerie (set) of the previous policies of the first two agents ( “shared_policy_2”).
My problem is that I see that the weights in the menagerie are overwritten in every iteration by the cur

[rllib] in torch custom_loss/ metrics are lost (don't show up in tensorboard)

Open

[tune] TuneSearchCV -> TypeError: 'NoneType' object is not callable

11

Find more good first issues →

horovod / horovod

Star

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

machine-learning spark deep-learning uber mxnet tensorflow mpi keras pytorch machinelearning baidu deeplearning ray

Updated Jul 2, 2021
Python

modin-project / modin

Star

Modin: Speed up your Pandas workflows by changing a single line of code

python sql pandas distributed datascience ray dataframe pandas-on-ray modin

Updated Jul 2, 2021
Python

mars-project / mars

Star

Open

Support `Series.between`

2

wjsi commented Dec 25, 2020

Support Series.between

Support Series.median()

1

Open

Support md.to_numeric

Find more good first issues →

erichlof / THREE.js-PathTracing-Renderer

Star

Real-time PathTracing with global illumination and progressive rendering, all on top of the Three.js WebGL framework. Click here for Live Demo: https://erichlof.github.io/THREE.js-PathTracing-Renderer/Geometry_Showcase.html

webgl threejs global-illumination path-tracer realtime path tracing raytracing tracer ray pathtracing three-js

Updated Jul 3, 2021
JavaScript

glouw / littlewolf

Star

A tiny software graphics and game engine

graphics engine raycaster doom casting wolfenstein ray

Updated Oct 1, 2020
C

LuxCoreRender / LuxCore

Star

LuxCore source repository

visualization opencl ray-tracer cuda raytracer raytracing gpu-computing ray ray-tracing 3d-graphics rtx optix pathtracer path-tracing bidirectional-path-tracing luxrender luxcorerender

Updated Jul 1, 2021
C++

yszhao91 / cga.js

Star

CGA 3D 计算几何算法库 | 3D Compute Geometry Algorithm Library webgl three.js babylon.js等任何库都可以使用

Updated Jun 28, 2021
JavaScript

rafael-fuente / Python-Raytracer

Star

A basic Ray Tracer that exploits numpy arrays and functions to work fast.

python fun rendering ray-tracer learning-python raytracer raytracing compile-time ray 3d-engine

Updated Apr 13, 2021
Python

EricSteinberger / PokerRL

Star

Framework for Multi-Agent Deep Reinforcement Learning in Poker

framework research reinforcement-learning poker deep-learning reinforcement-learning-algorithms ray gym-environment

Updated Jul 4, 2020
Python

dkeras-project / dkeras

Star

Distributed Keras Engine, Make Keras faster with only one line of code.

python distributed-systems machine-learning deep-neural-networks deep-learning neural-network tensorflow parallel-computing keras distributed ray keras-models keras-classification-models keras-neural-networks tensorflow-models keras-tensorflow data-parallelism distributed-deep-learning distributed-keras-engine plaidml

Updated Oct 3, 2019
Python

Draichi / T-1000

Star

⚡

⚡ 𝘋𝘦𝘦𝘱 𝘙𝘓 𝘈𝘭𝘨𝘰𝘵𝘳𝘢𝘥𝘪𝘯𝘨 𝘸𝘪𝘵𝘩 𝘙𝘢𝘺 𝘈𝘗𝘐

bot trading genetic-algorithm trading-bot algotrading rl ray reinforcement-learning-bot rllib

Updated Oct 23, 2020
Python

oap-project / raydp

Star

RayDP: Distributed data processing library that provides simple APIs for running Spark on Ray and integrating Spark with distributed deep learning and machine learning frameworks.

spark ray

Updated Jun 30, 2021
Python

cyoon1729 / distributedRL

Star

A framework for easy prototyping of distributed reinforcement learning algorithms

reinforcement-learning zeromq dqn ray distributed-reinforcement-learning ape-x

Updated Dec 8, 2020
Python

sjtu-marl / malib

Star

A parallel framework for population-based multi-agent reinforcement learning.

python games reinforcement-learning parallel distributed multiagent ray

Updated Jul 4, 2021
Python

ChuaCheowHuan / gym-continuousDoubleAuction

Star

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 Jun 8, 2021
Jupyter Notebook

kobanium / Ray

Star

Computer Go Program

go baduk weiqi ray

Updated Apr 13, 2021
C++

multi-commander / Multi-Commander

Star

Multi & Single Agent Reinforcement Learning for Traffic Signal Control Problem

reinforcement-learning multi-agent ray deecamp cityflow traffic-signal-control

Updated May 13, 2021
Python

kojiba / RayLanguage

Star

Additions to C functional. (Containers, strings operations, memory operations, sockets, threads, etc...)

c socket list cryptography encryption dictionary buffer array bytes lib hash linkedlist decryption ray pray navive winapi-posix std threads

Updated Jan 26, 2017
C

edap / ofxRaycaster

Star

Plane, 2D and 3D Ray objects for openFrameworks.It checks for the intersection of a ray with a segment, a sphere, a triangle, a plane, an ofPrimitive, an ofPolyline an with an ofMesh.

plane openframeworks addon intersection ray raycasting intersection-point 2d-ray intersection-methods