Liang Yanchang's repositories
agent-based-modeling-in-electricity-market-using-DDPG-algorithm
Agent-Based Modeling in Electricity Market Using Deep Deterministic Policy Gradient Algorithm
rainbow-is-all-you-need
Rainbow is all you need! Step-by-step tutorials from DQN to Rainbow
DeepRL-Tutorials
Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch
BMSpy
Python Block-Model Simulator. An alternative to simulink in python.
Deep-reinforcement-learning-with-pytorch
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
ESC-50
ESC-50: Dataset for Environmental Sound Classification
multiagent_rl
Multi-Agent Reinforcement Learning with Particle Env. (on going)
pumpkin-book
《机器学习》（西瓜书）公式推导解析，在线阅读地址：https://datawhalechina.github.io/pumpkin-book
pysmps
Utilities for parsing MPS and SMPS file formats.
pytorch-handbook
pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行
pytorch-rdpg
PyTorch Implementation of the RDPG (Recurrent Deterministic Policy Gradient)
Recurrent-Deep-Q-Learning
Solving POMDP using Recurrent networks
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
Implementation of REINFORCE algorithm in Pytorch
Reinforcement-Implementation
Implementation of benchmark RL algorithms
RL-Adventure-2
PyTorch0.4 implementation of: actor critic / proximal policy optimization / acer / ddpg / twin dueling ddpg / soft actor critic / generative adversarial imitation learning / hindsight experience replay