RobertTLange / gymnax-blinesLinks
Baselines for gymnax π€
β67Updated 2 years ago
Alternatives and similar repositories for gymnax-blines
Users that are interested in gymnax-blines are comparing it to the libraries listed below
Sorting:
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β56Updated 2 years ago
- β81Updated 3 months ago
- Contains JAX implementation of algorithms for inverse reinforcement learningβ73Updated 10 months ago
- JAX implementations of core Deep RL algorithmsβ79Updated 3 years ago
- General Modules for JAXβ65Updated 2 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRLβ113Updated 10 months ago
- Vectorization techniques for fast population-based training.β56Updated 2 years ago
- β80Updated 7 months ago
- Accelerated replay buffers in JAXβ41Updated 2 years ago
- Simple single-file baselines for Q-Learning in pure-GPU settingβ172Updated 3 months ago
- A collection of RL algorithms written in JAX.β98Updated 2 years ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorchβ51Updated 2 years ago
- JAX implementation of RL algorithms and vectorized environmentsβ46Updated last year
- Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselinβ¦β53Updated last month
- Benchmarking RL generalization in an interpretable way.β157Updated last week
- Accelerated minigrid environments with JAXβ139Updated 2 weeks ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!β226Updated last month
- Evaluating long-term memory of reinforcement learning algorithmsβ143Updated 2 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"β100Updated 3 years ago
- Novelty MiniGrid--NovGrid--is an extension of MiniGrid environment that allows for the world properties and dynamics to change according β¦β35Updated last year
- β41Updated 11 months ago
- Clean single-file implementation of offline RL algorithms in JAXβ146Updated 6 months ago
- πͺ The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAXβ57Updated last year
- An implementation of MuZero in JAX.β56Updated 2 years ago
- β47Updated 2 years ago
- impact-driven-explorationβ131Updated last year
- β‘ Flashbax: Accelerated Replay Buffers in JAXβ238Updated 2 months ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objectiveβ80Updated 2 years ago
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the β¦β86Updated 4 years ago
- β28Updated 2 years ago