oxwhirl / Treeqn
Licence: mit
Stars: ✭ 77
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Treeqn
Hierarchical Actor Critic Hac Pytorch
PyTorch implementation of Hierarchical Actor Critic (HAC) for OpenAI gym environments
Stars: ✭ 116 (+50.65%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Async Deeprl
Playing Atari games with TensorFlow implementation of Asynchronous Deep Q-Learning
Stars: ✭ 44 (-42.86%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Reinforcementlearning Atarigame
Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games
Stars: ✭ 118 (+53.25%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Cs234 Reinforcement Learning Winter 2019
My Solutions of Assignments of CS234: Reinforcement Learning Winter 2019
Stars: ✭ 93 (+20.78%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Rl a3c pytorch
A3C LSTM Atari with Pytorch plus A3G design
Stars: ✭ 482 (+525.97%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Deep Reinforcement Learning
Repo for the Deep Reinforcement Learning Nanodegree program
Stars: ✭ 4,012 (+5110.39%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
Stars: ✭ 980 (+1172.73%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Pytorch Rl
This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch
Stars: ✭ 394 (+411.69%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Rl Book
Source codes for the book "Reinforcement Learning: Theory and Python Implementation"
Stars: ✭ 464 (+502.6%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Mushroom Rl
Python library for Reinforcement Learning.
Stars: ✭ 442 (+474.03%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Btgym
Scalable, event-driven, deep-learning-friendly backtesting library
Stars: ✭ 765 (+893.51%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Hands On Reinforcement Learning With Python
Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow
Stars: ✭ 640 (+731.17%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Deterministic Gail Pytorch
PyTorch implementation of Deterministic Generative Adversarial Imitation Learning (GAIL) for Off Policy learning
Stars: ✭ 44 (-42.86%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning, openai-gym
Deepbootcamp
Solved lab problems, slides and notes of the Deep Reinforcement Learning bootcamp 2017 held at UCBerkeley
Stars: ✭ 39 (-49.35%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning
Deepqlearning.jl
Implementation of the Deep Q-learning algorithm to solve MDPs
Stars: ✭ 38 (-50.65%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning
Rl Course Experiments
Stars: ✭ 73 (-5.19%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning
1 Year Machinelearning Journey
An advanced program in Machine Learning and Deep Learning
Stars: ✭ 69 (-10.39%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning
Awesome Deep Rl
For deep RL and the future of AI.
Stars: ✭ 985 (+1179.22%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning
Deep Q Learning
Minimal Deep Q Learning (DQN & DDQN) implementations in Keras
Stars: ✭ 1,013 (+1215.58%)
Mutual labels: reinforcement-learning, deep-reinforcement-learning
Dmc2gym
OpenAI Gym wrapper for the DeepMind Control Suite
Stars: ✭ 75 (-2.6%)
Mutual labels: reinforcement-learning, openai-gym
TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning
Code of our ICLR 2018 paper.
Requirements
The code can be run in a docker container as described below. The dockerfile template in docker/Dockerfile.cuda.template lists all requirements that may be needed to set up a non-dockerised environment. The core requirements are pytorch, gym, and sacred.
Sacred
The configuration and logging is handled by Sacred. Results are stored by the FileStorageObserver as .json's in results/. We recommend a MongoObserver (requires pymongo) to organise larger numbers of experiments.
Options
Valid configuration options are documented in conf/default.yaml.
The default settings correspond to our Atari experiments on Seaquest with TreeQN, depth 2.
Running
To run a default setup with the configuration specified in conf/default.yaml, simply execute:
python treeqn/nstep_run.py
Further parameters can be specified using with:
python treeqn/nstep_run.py with env_id=Qbert architecture=dqn
Configuration files can also be used. Our box-pushing experiment defaults are given in conf/push.yaml:
python treeqn/nstep_run.py with config=./conf/push.yaml
If you have Docker installed, you can build a docker image tagged treeqn with:
cd docker
./build.sh
cd ..
To run an experiment in a detached docker container named treeqn-$GPU_ID, use:
./docker/run.sh $GPU_ID python treeqn/nstep_run.py
Citation
@inproceedings{farquhar2018treeqn,
title={TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning},
author={Farquhar, Gregory and Rockt{\"a}schel, Tim and Igl, Maximilian and Whiteson, Shimon},
booktitle={ICLR 2018},
year={2018}
}
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].