aiworld / dqn
Deep Q-learning with Caffe on Space Invaders
☆19Updated 9 years ago
Related projects ⓘ
Alternatives and complementary repositories for dqn
- [deprecated] Bridge from Gym to ROS robots☆75Updated last year
- Deep reinforcement learning-driven robotic controller and navigation library using Torch.☆34Updated 7 years ago
- Driving in TORCS using Caffe following Direct Perception approach☆47Updated 8 years ago
- Fourth Project of the Udacity Self-Driving Car Nanodegree Program☆32Updated 7 years ago
- tensorflow deep RL for driving a rover around☆64Updated 7 years ago
- Pack of Drones: Layered reinforcement learning (Q-learning w/ RNN) for complex "hunt" behaviors☆61Updated 8 years ago
- reinfore learning tool box, contains trpo, a3c algorithm for continous action space☆43Updated 6 years ago
- Torch7/lua wrapper of roscpp via ffi.☆20Updated 6 years ago
- GoPiGo robot driven autonomously by trained CNN using retrained Tensorflow Inception☆69Updated 6 years ago
- Playing Atari games with TensorFlow implementation of Asynchronous Deep Q-Learning☆43Updated 6 years ago
- ☆6Updated 8 years ago
- OverFeat-Torch7 Wrapper Library☆44Updated 8 years ago
- Quadrotor simulator mainly purposed to train neural network to control quadrotor flight via deep q learning algorithm☆26Updated 2 years ago
- Universal library for deep reinforcement learning.☆39Updated 8 years ago
- Unsupervised learning of visual concepts from video☆57Updated 8 years ago
- Tensorflow implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"☆48Updated 7 years ago
- Estimate road layout attributes given street view imagery☆29Updated 7 years ago
- RNN for producing text to handwriting image☆31Updated 7 years ago
- A Quick and Dirty Progressive Neural Network written in TensorFlow.☆53Updated 6 years ago
- TensorFlow implementation of Value Iteration Networks (VIN): Clean, Simple and Modular☆53Updated 7 years ago
- A Tensorflow based implementation of "Asynchronous Methods for Deep Reinforcement Learning": https://arxiv.org/abs/1602.01783☆68Updated 8 years ago
- Asynchronous One Step Q Learning implemented with MXNET☆20Updated 7 years ago
- Modified tensorflow implementation of 'Asynchronous Methods for Deep Reinforcement Learning'☆22Updated 7 years ago
- Convolutional (Patch) Networks for Semantic Segmentation☆123Updated 3 years ago
- A python client for the Simulated Car Race Championship☆40Updated 12 years ago
- ROS nodes for visualization, calibration, car and passenger detection for Didi autonomous driving competition.☆14Updated 7 years ago
- Car autopilot software that uses C++, BVLC Caffe, OpenCV, and SFML☆65Updated 8 years ago
- ☆19Updated 8 years ago