nimishsantosh107 / Reinforcement-Learning Public

Notifications You must be signed in to change notification settings
Fork 0
Star 3

Reinforcement learning algorithms and solved gym environments.

3 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 42 Commits
algorithms		algorithms
gym		gym
papers		papers
.gitignore		.gitignore
README.md		README.md

Repository files navigation

Reinforcement Learning

Repo contains notebooks with common reinforcement learning algorithms and solved gym environments.

Value Based Methods

Algorithms	Paper & Code
Q-Learning & SARSA	notebook
DQN	notebook DQN paper
DoubleDQN	notebook DoubleDQN paper
DuelingDQN	notebook DuelingDQN paper
`DuelingDoubleDQN + PER`	notebook PER paper

Policy Based Methods

Algorithms	Paper & Code
PG(Reinforce)	notebook
`PPO` [needs improvement]	notebook (discrete) notebook (continuous) PPO paper

Actor Critic Methods

Algorithms	Paper & Code
AC	notebook AC paper
`A2C`	notebook (discrete) A3C paper
`DDPG`	notebook DDPG paper
`TD3`	notebook TD3 paper

About

Reinforcement learning algorithms and solved gym environments.

reinforcement-learning openai-gym pytorch dqn ddpg ddqn ppo td3 dueling-ddqn

Report repository

Releases

No releases published

Packages

Languages

Jupyter Notebook 100.0%