Using a paper from Google DeepMind I've developed a new version of the DQN using threads exploration instead of memory replay as explain in here: http://arxiv.org/pdf/1602.01783v1.pdf I used the one-step-Q-learning pseudocode, and now we can train the Pong game in less than 20 hours and without any GPU or network distribution.
☆84Mar 4, 2016Updated 9 years ago
Alternatives and similar repositories for Asynchronous-Methods-for-Deep-Reinforcement-Learning
Users that are interested in Asynchronous-Methods-for-Deep-Reinforcement-Learning are comparing it to the libraries listed below
Sorting:
- Torch implementation of "Deep Exploration via Bootstrapped DQN"☆42Apr 10, 2016Updated 9 years ago
- An implementation of Deep Reinforcement Learning / Deep Q-Networks for Atari games in TensorFlow☆74Feb 25, 2017Updated 9 years ago
- Replicating "Asynchronous Methods for Deep Reinforcement Learning" (http://arxiv.org/abs/1602.01783)☆408Feb 25, 2017Updated 9 years ago
- Asynchronous Methods for Deep Reinforcement Learning☆591Aug 9, 2018Updated 7 years ago
- A Tensorflow based implementation of "Asynchronous Methods for Deep Reinforcement Learning": https://arxiv.org/abs/1602.01783☆68Oct 28, 2016Updated 9 years ago
- Implementation of a simple example of Q learning in Torch.☆51Mar 5, 2017Updated 8 years ago
- Gated Recurrent Unit with Low-rank matrix factorization☆34Mar 11, 2016Updated 9 years ago
- Dynamic Capacity Networks using Tensorflow☆52Feb 15, 2017Updated 9 years ago
- Deterministic Policy Gradient using torch7☆43Jun 2, 2016Updated 9 years ago
- Deep Attention Recurrent Q-Network☆115Nov 7, 2015Updated 10 years ago
- Collection of reinforcement learners implemented in python. Mainly including DQN and its variants☆54Apr 23, 2017Updated 8 years ago
- Torch implementation for Robust convolutional neural networks under adversarial noise☆13Mar 8, 2016Updated 9 years ago
- KEras Reinforcement Learning gYM agents☆291Jul 8, 2017Updated 8 years ago
- Universal library for deep reinforcement learning.☆38Apr 15, 2016Updated 9 years ago
- TensorFlow implementation of the DDPG algorithm from the paper Continuous Control with Deep Reinforcement Learning (ICLR 2016)☆215Feb 16, 2018Updated 8 years ago
- Persistent advantage learning dueling double DQN for the Arcade Learning Environment☆263Feb 8, 2018Updated 8 years ago
- RC-NFQ: Regularized Convolutional Neural Fitted Q Iteration. A batch algorithm for deep reinforcement learning. Incorporates dropout regu…☆12Mar 17, 2021Updated 4 years ago
- Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"☆1,008Mar 18, 2018Updated 7 years ago
- Pack of Drones: Layered reinforcement learning (Q-learning w/ RNN) for complex "hunt" behaviors☆63Jun 12, 2016Updated 9 years ago
- AI Final Project☆65Jan 17, 2016Updated 10 years ago
- Code base for solving Markov Decision Processes and Reinforcement Learning problems using Recurrent Convolutional Neural Networks.☆69Oct 29, 2017Updated 8 years ago
- Variation of "Asynchronous Methods for Deep Reinforcement Learning" with multiple processes generating experience for agent (Keras + Thea…☆44Feb 27, 2018Updated 8 years ago
- hierarchical deep reinforcement learning algorithms☆43Dec 12, 2017Updated 8 years ago
- Low-rank Highway Networks☆13Mar 11, 2016Updated 9 years ago
- ☆24Jun 9, 2016Updated 9 years ago
- ☆28Apr 28, 2019Updated 6 years ago
- Convolution neural network... for draw video poker. Perhaps, we learn something useful for other poker, too.☆109Feb 13, 2016Updated 10 years ago
- Implementation of "Action-Conditional Video Prediction using Deep Networks in Atari Games"☆114Feb 8, 2016Updated 10 years ago
- A deep Q learning demonstration using Google Tensorflow☆1,165May 24, 2017Updated 8 years ago
- Unsupervised learning of visual concepts from video☆56May 5, 2016Updated 9 years ago
- ☆98Aug 25, 2016Updated 9 years ago
- ☆18Dec 11, 2015Updated 10 years ago
- Implementation of the paper [Using Fast Weights to Attend to the Recent Past](https://arxiv.org/abs/1610.06258)☆174Nov 3, 2016Updated 9 years ago
- Python implementation of tabular asynchronous actor critic☆11May 3, 2016Updated 9 years ago
- Proof of concept prototype to perform distributed training using BVLC/caffe, based on a parameter server implementation using MPI. Data p…☆13May 7, 2015Updated 10 years ago
- Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.☆661Feb 25, 2020Updated 6 years ago
- Query-Reduction Networks (QRN)☆138Dec 20, 2017Updated 8 years ago
- LSTM with associative memory cells (http://arxiv.org/abs/1602.03032)☆109May 1, 2016Updated 9 years ago
- Study of HeXA@UNIST in Preparation for Submission☆107May 19, 2016Updated 9 years ago