vwxyzjn / cleanbaLinks
CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL
☆118Updated last year
Alternatives and similar repositories for cleanba
Users that are interested in cleanba are comparing it to the libraries listed below
Sorting:
- ☆88Updated last year
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆59Updated 3 years ago
- ☆88Updated 3 months ago
- Accelerated replay buffers in JAX☆45Updated 3 years ago
- General Modules for JAX☆71Updated 2 months ago
- Baselines for gymnax 🤖☆73Updated 2 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆103Updated 3 years ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆105Updated last year
- Contains JAX implementation of algorithms for inverse reinforcement learning☆74Updated last year
- An implementation of MuZero in JAX.☆57Updated 3 years ago
- ☆46Updated last year
- Extreme Q-Learning: Max Entropy RL without Entropy☆87Updated 2 years ago
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.☆137Updated last year
- Vectorization techniques for fast population-based training.☆56Updated 3 years ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆226Updated 2 weeks ago
- JAX implementations of core Deep RL algorithms☆82Updated 3 years ago
- Evaluating long-term memory of reinforcement learning algorithms☆154Updated 2 years ago
- A collection of RL algorithms written in JAX.☆104Updated 3 years ago
- Accelerated minigrid environments with JAX☆153Updated last month
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆60Updated 2 years ago
- Efficient baselines for autocurricula in JAX.☆201Updated last year
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆110Updated 2 years ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆128Updated 5 months ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"☆50Updated last year
- ☆243Updated last year
- Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselin…☆62Updated 2 weeks ago
- ☆52Updated 2 years ago
- Corax: Core RL in JAX☆38Updated last year
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆92Updated 4 years ago
- Datasets for data-driven deep reinforcement learning with Atari (wrapper for datasets released by Google)☆127Updated last year