facebookresearch / e3b
Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".
β82Updated 11 months ago
Alternatives and similar repositories for e3b:
Users that are interested in e3b are comparing it to the libraries listed below
- Evaluating long-term memory of reinforcement learning algorithmsβ141Updated last year
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRLβ109Updated 6 months ago
- Baselines for gymnax π€β66Updated last year
- Discovering and Achieving Goals via World Models, NeurIPS 2021β85Updated last year
- General Modules for JAXβ64Updated 2 weeks ago
- impact-driven-explorationβ130Updated last year
- Contains JAX implementation of algorithms for inverse reinforcement learningβ69Updated 6 months ago
- β74Updated 6 months ago
- Simple single-file baselines for Q-Learning in pure-GPU settingβ141Updated 3 months ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"β53Updated 11 months ago
- β100Updated last year
- β28Updated 2 years ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objectiveβ79Updated 2 years ago
- Deep Hierarchical Planning from Pixelsβ94Updated 2 years ago
- β43Updated last year
- TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.β69Updated last year
- β27Updated last year
- [NeurIPS 2022] Open source code for reusing prior computational work in RL.β95Updated last year
- The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learningβ¦β61Updated last year
- PAIRED in PyTorch π₯β58Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β53Updated 2 years ago
- MultiTask Environments for Reinforcement Learning.β74Updated 2 years ago
- Synchronized Curriculum Learning for RL Agentsβ41Updated 2 weeks ago
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.β130Updated 6 months ago
- Open source code for paper "Denoised MDPs: Learning World Models Better Than the World Itself"β136Updated last year
- A tool for recording RL trajectories.β100Updated 4 months ago
- CIC: Contrastive Intrinsic Control for Unsupervised Skill Discoveryβ80Updated 2 years ago
- Challenging Memory-based Deep Reinforcement Learning Agentsβ93Updated 4 months ago
- β41Updated 8 months ago