cvhu / CliffWalking
Comparison between Sarsa and Q-Learning algorithms on risk handling
☆17Updated 7 years ago
Related projects: ⓘ
- ☆42Updated 5 years ago
- Deep Reinforcement Learning with Fined Grained Action Repetition☆23Updated 6 years ago
- Combining deep learning and reinforcement learning.☆81Updated 2 years ago
- ☆30Updated 6 years ago
- ☆57Updated last year
- ☆50Updated 5 years ago
- Optimized Differentiable Neural Computer In Chainer☆23Updated 6 years ago
- Tensorflow implementation of Neural Arithmetic Logic Unit, Trask et al.☆29Updated 6 years ago
- ☆8Updated 7 years ago
- Deep RL Bootcamp solutions☆35Updated 6 years ago
- Trained models for keras-rl.☆21Updated 7 years ago
- InfoGAN Implementation in PyTorch☆20Updated 6 years ago
- ☆29Updated this week
- ☆39Updated 6 years ago
- Unsupervised Deep Learning and Representation Learning Tutorial☆13Updated 8 years ago
- Code for my blog post "Design by Evolution"☆21Updated 6 years ago
- ☆24Updated 8 years ago
- Our NIPS 2017: Learning to Run source code☆56Updated last year
- Attempt at reinforcement learning with curiosity for Sonic the Hedgehog games. Number 149 on OpenAI retro contest leaderboard, but more w…☆31Updated 6 years ago
- Code base for solving Markov Decision Processes and Reinforcement Learning problems using Recurrent Convolutional Neural Networks.☆69Updated 6 years ago
- ☆61Updated last year
- [DEPRECATED] Advantage Actor Critic model in PyTorch inspired by OpenAI baselines TensorFlow implementation