openai / train-procgen
Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"
☆169Updated last year
Related projects ⓘ
Alternatives and complementary repositories for train-procgen
- impact-driven-exploration☆126Updated last year
- OpenAI Gym wrapper for the DeepMind Control Suite☆204Updated 5 months ago
- Code for the paper "Phasic Policy Gradient"☆251Updated last year
- Vectorized interface for reinforcement learning environments☆141Updated last year
- Starter Kit for NeurIPS 2020 - Procgen Competition on AIcrowd☆90Updated last year
- Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"☆156Updated 2 years ago
- Repository for the paper "Planning to Explore via Self-Supervised World Models"☆215Updated last year
- Code for "Unsupervised State Representation Learning in Atari"☆242Updated last year
- Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO☆191Updated 2 years ago
- ☆285Updated last year
- Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.☆285Updated 9 months ago
- MultiTask Environments for Reinforcement Learning.☆74Updated 2 years ago
- Keeping track of RL experiments☆159Updated last year
- Multi Task RL Baselines☆223Updated 2 years ago
- PAIRED in PyTorch 🔥☆56Updated last year
- Evaluating long-term memory of reinforcement learning algorithms☆132Updated last year
- A networking protocol for agent-environment communication☆91Updated last month
- pytorch-implementation of Dreamer (Model-based Image RL Algorithm)☆162Updated 2 years ago
- DrQ: Data regularized Q☆406Updated last year
- Datasets for data-driven deep reinforcement learning with PyBullet environments☆143Updated 3 years ago
- Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)☆181Updated last year
- Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined wit…☆186Updated 3 years ago
- OpenAI Gym wrapper for ViZDoom enviroments☆66Updated 3 years ago
- ☆331Updated 2 years ago
- Multitask Environments for RL☆273Updated 3 years ago
- Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)☆68Updated last year
- ☆188Updated last year
- Deep Planning Network: Control from pixels by latent planning with learned dynamics☆365Updated 3 years ago
- A Python interface for reinforcement learning environments☆344Updated last year
- DrQ-v2: Improved Data-Augmented Reinforcement Learning☆353Updated 2 years ago