openai / retro-baselines
Publicly releasable baselines for the Retro contest
☆128Updated 5 years ago
Related projects: ⓘ
- ☆117Updated 4 years ago
- A reinforcement learning framework☆154Updated 5 years ago
- OpenAI Retro Contest☆65Updated 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"☆195Updated 5 years ago
- NIPS 2017 Value Prediction Network☆165Updated 6 years ago
- Noisy Networks for Exploration☆184Updated 6 years ago
- Implementations of deep RL papers and random experimentation☆177Updated 6 years ago
- Training Sonic with RLlib☆56Updated last year
- Codes of our team for the OpenAI Retro Contest of reinforcement learning☆100Updated 6 years ago
- A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release th…☆201Updated 4 years ago
- A working implementation of the Categorical DQN (Distributional RL).☆96Updated 6 years ago
- ☆161Updated 7 years ago
- Gym - Doom environments based on VizDoom.☆102Updated 7 years ago
- Source code for OpenAI Retro Contest for Sonic the Hedgehog☆30Updated 6 years ago
- Accompanying code for "Deep Reinforcement Learning that Matters"☆153Updated 6 years ago
- This repo is intended as an extension for OpenAI Gym for auxiliary tasks (multitask learning, transfer learning, inverse reinforcement le…☆213Updated 5 years ago
- ☆99Updated 8 years ago
- Reason8.ai PyTorch solution for NIPS RL 2017 challenge☆84Updated 4 years ago
- Direct Future Prediction (DFP ) in Keras☆109Updated 6 years ago
- Reinforcement learning models in ViZDoom environment☆131Updated 2 years ago
- Easy TensorFlow logging for quick prototypes☆110Updated 2 years ago
- Code for the paper "Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments"☆299Updated last year
- World Models applied to the Open AI Sonic Retro Contest☆77Updated 6 years ago
- C51-DDQN in Keras☆125Updated 6 years ago
- Implementation of "Control of Memory, Active Perception, and Action in Minecraft"☆86Updated 7 years ago
- A TensorFlow implementation of DeepMind's A Distributional Perspective on Reinforcement Learning.(C51-DQN)☆56Updated 7 years ago
- Code for the paper "Learning to Act by Predicting the Future", Alexey Dosovitskiy and Vladlen Koltun, ICLR 2017☆150Updated 2 weeks ago
- RUDDER for ATARI games with delayed rewards in OpenAI Baselines package☆265Updated 4 years ago
- Building Agents with Imagination: pytorch step-by-step implementation☆205Updated 5 years ago