ethanluoyc / magi
Reinforcement learning library in JAX.
☆103Updated last year
Related projects ⓘ
Alternatives and complementary repositories for magi
- JAX implementations of core Deep RL algorithms☆79Updated 2 years ago
- Baselines for gymnax 🤖☆58Updated last year
- Vectorization techniques for fast population-based training.☆54Updated 2 years ago
- ☆100Updated 8 months ago
- ☆61Updated 2 months ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆49Updated 2 years ago
- A collection of RL algorithms written in JAX.☆94Updated 2 years ago
- PAIRED in PyTorch 🔥☆56Updated last year
- Model-based reinforcement learning in TensorFlow☆53Updated 3 years ago
- General Modules for JAX☆58Updated 3 months ago
- An implementation of MuZero in JAX.☆53Updated 2 years ago
- On the model-based stochastic value gradient for continuous reinforcement learning☆55Updated last year
- Contains JAX implementation of algorithms for inverse reinforcement learning☆62Updated 2 months ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆79Updated last year
- Modular framework for Reinforcement Learning in python☆166Updated last year
- Revisiting Rainbow☆73Updated 3 years ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆105Updated 2 months ago
- Fully differentiable RL environments, written in Ivy.☆62Updated last year
- A tool for recording RL trajectories.☆93Updated 2 weeks ago
- ☆147Updated 2 months ago
- Accelerated minigrid environments with JAX☆113Updated 3 months ago
- Performant, differentiable reinforcement learning☆121Updated 4 months ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- Conservative Q learning in Jax☆50Updated last year
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- ☆116Updated last year
- ☆64Updated this week
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆83Updated 3 years ago
- MultiTask Environments for Reinforcement Learning.☆74Updated 2 years ago
- Pytorch starter code for UC Berkeley's cs285 assignments☆70Updated 2 years ago