automl / CARLLinks
Benchmarking RL generalization in an interpretable way.
☆168Updated 3 weeks ago
Alternatives and similar repositories for CARL
Users that are interested in CARL are comparing it to the libraries listed below
Sorting:
- Partially Observable Process Gym☆204Updated 5 months ago
- Evaluating long-term memory of reinforcement learning algorithms☆150Updated 2 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆102Updated 3 years ago
- Datasets for data-driven deep reinforcement learning with Atari (wrapper for datasets released by Google)☆127Updated last year
- Simple maze environments using mujoco-py☆56Updated last year
- Author's PyTorch implementation of TD7 for online and offline RL☆153Updated 2 years ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆104Updated last year
- Representation Learning for RL☆128Updated 2 years ago
- Clean single-file implementation of offline RL algorithms in JAX☆159Updated 10 months ago
- Deep Hierarchical Planning from Pixels☆109Updated 2 years ago
- ☆241Updated 11 months ago
- OpenAI Gym wrapper for the DeepMind Control Suite☆223Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆188Updated 7 months ago
- ☆355Updated 3 years ago
- Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"☆80Updated last year
- ☆203Updated 2 years ago
- Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)☆197Updated 2 years ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"☆50Updated last year
- ExORL: Exploratory Data for Offline Reinforcement Learning☆117Updated 3 years ago
- Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.☆192Updated last month
- ☆48Updated 2 years ago
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.☆135Updated last year
- A collection of RL algorithms written in JAX.☆104Updated 3 years ago
- LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization☆38Updated 2 years ago
- Skeleton for scalable and flexible Jax RL implementations☆88Updated 2 years ago
- Code accompanying the paper Adversarially Trained Actor Critic for Offline Reinforcement Learning by Ching-An Cheng*, Tengyang Xie*, Nan …☆71Updated 2 years ago
- Code for MOPO: Model-based Offline Policy Optimization☆188Updated 3 years ago
- ☆45Updated 2 years ago
- Conservative Q Learning on top of SAC☆132Updated 3 years ago
- Pytorch version of Dreamer, which follows the original TF v2 codes.☆132Updated 3 years ago