openai / retro-baselinesLinks
Publicly releasable baselines for the Retro contest
☆127Updated 6 years ago
Alternatives and similar repositories for retro-baselines
Users that are interested in retro-baselines are comparing it to the libraries listed below
Sorting:
- A reinforcement learning framework☆155Updated 6 years ago
- ☆117Updated 4 years ago
- OpenAI Retro Contest☆65Updated 2 years ago
- NIPS 2017 Value Prediction Network☆166Updated 7 years ago
- Codes of our team for the OpenAI Retro Contest of reinforcement learning☆99Updated 7 years ago
- Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"☆201Updated 6 years ago
- Gym - Doom environments based on VizDoom.☆103Updated 8 years ago
- A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release th…☆202Updated 5 years ago
- Easy TensorFlow logging for quick prototypes☆110Updated 3 years ago
- A working implementation of the Categorical DQN (Distributional RL).☆96Updated 7 years ago
- Accompanying code for "Deep Reinforcement Learning that Matters"☆152Updated 7 years ago
- A parallel version of Trust Region Policy Optimization☆65Updated 8 years ago
- This repo replicates the results Horgan et al obtained in "Distributed Prioritized Experience Replay"☆190Updated 6 years ago
- Training Sonic with RLlib☆59Updated 2 years ago
- Code for the paper "Evolved Policy Gradients"☆250Updated 6 years ago
- World Models applied to the Open AI Sonic Retro Contest☆77Updated 6 years ago
- Reason8.ai PyTorch solution for NIPS RL 2017 challenge☆84Updated 5 years ago
- Source code for OpenAI Retro Contest for Sonic the Hedgehog☆31Updated 6 years ago
- C51-DDQN in Keras☆126Updated 7 years ago
- Implementations of deep RL papers and random experimentation☆176Updated 7 years ago
- A TensorFlow based implementation of the DeepMind Atari playing "Deep Q Learning" agent that works reasonably well☆91Updated 8 years ago
- Reinforcement learning models in ViZDoom environment☆131Updated 3 years ago
- ☆101Updated 8 years ago
- This repo is intended as an extension for OpenAI Gym for auxiliary tasks (multitask learning, transfer learning, inverse reinforcement le…☆215Updated 5 years ago
- ☆159Updated 7 years ago
- Asynchronous Methods for Deep Reinforcement Learning☆38Updated 8 years ago
- Noisy Networks for Exploration☆185Updated 7 years ago
- ViZDoom Python wrapper☆74Updated 2 years ago
- A TensorFlow implementation of DeepMind's A Distributional Perspective on Reinforcement Learning.(C51-DQN)☆57Updated 7 years ago
- "Continuous Deep Q-Learning with Model-based Acceleration" in TensorFlow☆192Updated 6 years ago