GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → rldotai → rl-algorithms

rldotai / rl-algorithms

Licence: MIT license
Reinforcement learning algorithms

Programming Languages

python
139335 projects - #7 most used programming language
C++
36643 projects - #6 most used programming language

Labels

algorithmreinforcement-learningreinforcement-learning-algorithmsfunction-approximationrl-algorithmslinear-function-approximation

Projects that are alternatives of or similar to rl-algorithms

Deep Reinforcement Learning
Repo for the Deep Reinforcement Learning Nanodegree program
Stars: ✭ 4,012 (+9930%)
Mutual labels:  reinforcement-learning-algorithms, rl-algorithms
Reinforcement-Learning-CheatSheet
Cheatsheet of Reinforcement Learning (Based on Sutton-Barto Book - 2nd Edition)
Stars: ✭ 22 (-45%)
Mutual labels:  reinforcement-learning-algorithms
connect4
Solving board games like Connect4 using Deep Reinforcement Learning
Stars: ✭ 33 (-17.5%)
Mutual labels:  reinforcement-learning-algorithms
xingtian
xingtian is a componentized library for the development and verification of reinforcement learning algorithms
Stars: ✭ 229 (+472.5%)
Mutual labels:  reinforcement-learning-algorithms
TD3-BipedalWalkerHardcore-v2
Solve BipedalWalkerHardcore-v2 with TD3
Stars: ✭ 41 (+2.5%)
Mutual labels:  reinforcement-learning-algorithms
Recurrent-Deep-Q-Learning
Solving POMDP using Recurrent networks
Stars: ✭ 52 (+30%)
Mutual labels:  reinforcement-learning-algorithms
pytorch-rl
Pytorch Implementation of RL algorithms
Stars: ✭ 15 (-62.5%)
Mutual labels:  reinforcement-learning-algorithms
marltoolbox
A toolbox with the goal of speeding up research on bargaining in MARL (cooperation problems in MARL).
Stars: ✭ 25 (-37.5%)
Mutual labels:  reinforcement-learning-algorithms
POMDP
Implementing a RL algorithm based upon a partially observable Markov decision process.
Stars: ✭ 31 (-22.5%)
Mutual labels:  reinforcement-learning-algorithms
Deep-rl-mxnet
Mxnet implementation of Deep Reinforcement Learning papers, such as DQN, PG, DDPG, PPO
Stars: ✭ 26 (-35%)
Mutual labels:  reinforcement-learning-algorithms
Upside-Down-Reinforcement-Learning
Upside-Down Reinforcement Learning (⅂ꓤ) implementation in PyTorch. Based on the paper published by Jürgen Schmidhuber.
Stars: ✭ 64 (+60%)
Mutual labels:  reinforcement-learning-algorithms
course-content-dl
NMA deep learning course
Stars: ✭ 537 (+1242.5%)
Mutual labels:  reinforcement-learning-algorithms
reinforced-race
A model car learns driving along a track using reinforcement learning
Stars: ✭ 37 (-7.5%)
Mutual labels:  reinforcement-learning-algorithms
PyPOMDP
Python implementation of POMDP framework and PBVI & POMCP algorithms.
Stars: ✭ 60 (+50%)
Mutual labels:  reinforcement-learning-algorithms
reinforcement-learning-resources
A curated list of awesome reinforcement courses, video lectures, books, library and many more.
Stars: ✭ 38 (-5%)
Mutual labels:  reinforcement-learning-algorithms
VREP-RL-bot
Reinforcement Learning in Vrep
Stars: ✭ 14 (-65%)
Mutual labels:  reinforcement-learning-algorithms
vsrl-framework
The Verifiably Safe Reinforcement Learning Framework
Stars: ✭ 42 (+5%)
Mutual labels:  reinforcement-learning-algorithms
agentmodels.org
Modeling agents with probabilistic programs
Stars: ✭ 66 (+65%)
Mutual labels:  reinforcement-learning-algorithms
RL-code-resources
A collection of Reinforcement Learning GitHub code resources divided by frameworks and environments
Stars: ✭ 51 (+27.5%)
Mutual labels:  reinforcement-learning-algorithms
Neural-Fictitous-Self-Play
Scalable Implementation of Neural Fictitous Self-Play
Stars: ✭ 52 (+30%)
Mutual labels:  reinforcement-learning-algorithms
View All Similar Projects ➔

rl-algorithms

Reinforcement learning algorithms.

There are many different variants on the basic ideas of reinforcement learning. I have implemented some of them, with a focus on linear function approximation.

Extending these algorithms (for example, with nonlinear function approximators such as neural nets) is relatively straightforward once you are familiar with the underlying ideas.

To facilitate this, the algorithms listed are written in a straightforward style and thoroughly commented, with references to the relevant papers and some explanation of the reasoning behind the code.

Implemented Algorithms

TODO

  • Q-Learning
  • SARSA
  • Distributional RL algorithms
  • Other second-order TD algorithms (e.g., NTD)
  • Actor-Critic algorithms

Contributing

Send me a pull request if you have code to contribute.

Alternatively, raise an issue and provide me with a link to the paper describing the algorithm, and I will read and implement it when I get a chance.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].