bravetodo Goto Github PK

a3c_continuous

A continuous action space version of A3C LSTM in pytorch plus A3G design

botfightevolution

A simple game with an reinforcement learning powered AI

deepmind_mas_enviroment

some Multiagent enviroment in 《Multi-agent Reinforcement Learning in Sequential Social Dilemmas》 and 《Value-Decomposition Networks For Cooperative Multi-Agent Learning》

drlplayground

A deep reinforcement learning playground with Unity running the game physics, and Python handling the reinforcement learning algorithms.

library

这个仓库是，学习一些库过程中做的一些练习

madrl

Repo containing code for multi-agent deep reinforcement learning (MADRL).

qtran

（QTRAN算法复现）There will be updates later

ray-zh-doc

recurrent-multiagent-deep-deterministic-policy-gradient-with-difference-rewards

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging simulated continuous control single agent tasks. These methods have further been extended to multiagent domains in cooperative, competitive or mixed environments. This paper primarily focuses on multiagent cooperative settings which can be modeled for several real world problems such as coordination of autonomous vehicles and warehouse robots. However, these systems suffer from several challenges such as, structural credit assignment and partial observability. In this paper, we propose Recurrent Multiagent Deep Deterministic Policy Gradient (RMADDPG) algorithm which extends Multiagent Deep Determinisitic Policy Gradient algorithm - MADDPG \cite{lowe2017multi} by using a recurrent neural network for the actor policy. This helps to address partial observability by maintaining a sequence of past observations which networks learn to preserve in order to solve the POMDP. In addition, we use reward shaping through difference rewards to address structural credit assignment in a partially observed environment. We evaluate the performance of MADDPG and R-MADDPG with and without reward shaping in a Multiagent Particle Environment. We further show that reward shaped RMADDPG outperforms the baseline algorithm MADDPG in a partially observable environmental setting.

reinforce

reinforcement learning

reproduce-results-reinforcement-learning-of-coordination-in-cooperative-multi-agent-systems

reproducing some of the results from "Reinforcement Learning of Coordination in Cooperative Multi-agent Systems"

sac

Soft Actor-Critic

tensoragent

Deep reinforcement learning agents implement by tensorflow

tensorflow-tutorial

Tensorflow tutorial from basic to hard

testtool

一些自己写的测试工具

unity-python

Python plugin for Unity3D

unity3d-python-communication

:zap: A very simple, fast, and general inter-process communication example between Unity3D C# and Python, using ZeroMQ

wuenda

这个仓库是吴恩达的深度学习、机器学习、tensorflow2的课程程序和作业题。如果想看，哪些程序是别人写的，看简介