openai / sonic-on-ray
Training Sonic with RLlib
☆56Updated last year
Related projects: ⓘ
- OpenAI Retro Contest☆65Updated last year
- Publicly releasable baselines for the Retro contest☆128Updated 5 years ago
- Source code for OpenAI Retro Contest for Sonic the Hedgehog☆30Updated 6 years ago
- Add-on package to gym, to record sequences of actions, observations, and rewards☆70Updated last year
- ☆117Updated 4 years ago
- A Tensorflow implementation of Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning☆32Updated 6 years ago
- Reinforcement Learning Assembly☆92Updated 3 years ago
- Some hard problems for reinforcement learning.☆32Updated 5 years ago
- Reason8.ai PyTorch solution for NIPS RL 2017 challenge☆84Updated 4 years ago
- ☆57Updated last year
- A parallel version of Trust Region Policy Optimization☆65Updated 7 years ago
- Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"☆30Updated 5 years ago
- A platform of grid world that supports up to 1 million reinforcement-learning agents.☆70Updated 7 years ago
- Models built with TensorFlow☆25Updated 5 years ago
- Our NIPS 2017: Learning to Run source code☆56Updated last year
- TensorFlow A2C to solve Acrobot, with synchronized parallel environments☆35Updated 6 years ago
- ☆44Updated 5 years ago
- Add-on for OpenAI Gym that supports automatic downloading of user environments.☆45Updated 7 years ago
- Tutorial on continuous control at Reinforcement Learning Summer School 2017.☆34Updated 7 years ago
- ☆30Updated 6 years ago
- Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning☆80Updated 6 years ago
- A working implementation of the Categorical DQN (Distributional RL).☆96Updated 6 years ago
- ☆42Updated 5 years ago
- Surprise-based intrinsic motivation for deep reinforcement learning☆20Updated 7 years ago
- A TensorFlow implementation of DeepMind's A Distributional Perspective on Reinforcement Learning.(C51-DQN)☆56Updated 7 years ago
- Wikipedia navigation environment for OpenAI Gym☆41Updated last year
- ☆24Updated 8 years ago
- Implementation is mostly based on Sergey Levine work (http://www.eecs.berkeley.edu/~svlevine/).☆43Updated 9 years ago
- Code accompanying the OptionGAN paper.☆43Updated 6 years ago
- Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"☆195Updated 5 years ago