seohongpark / ogbenchLinks
A benchmark for offline goal-conditioned RL and offline RL
☆189Updated this week
Alternatives and similar repositories for ogbench
Users that are interested in ogbench are comparing it to the libraries listed below
Sorting:
- ☆289Updated 2 years ago
- ☆93Updated 3 months ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆85Updated 6 months ago
- Goal-Conditioned Reinforcement Learning with JAX☆169Updated last month
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆75Updated last year
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations☆103Updated last year
- Repo for Implicit Diffusion Q-Learning☆109Updated last year
- official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning☆98Updated 10 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- A PyTorch implementation of Implicit Behavioral Cloning☆106Updated 2 years ago
- Transformer-based World Models☆82Updated 2 years ago
- Skeleton for scalable and flexible Jax RL implementations☆82Updated last year
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆70Updated last year
- Code and website for Behavior Transformers: Cloning k modes with one stone.☆125Updated 2 years ago
- Foundation Policies with Hilbert Representations (ICML 2024)☆88Updated last year
- JAX implementation of WSRL and RL baselines | ICLR 2025☆44Updated last month
- Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"☆75Updated last year
- Unified Implementations of Offline Reinforcement Learning Algorithms☆80Updated last month
- ☆48Updated 7 months ago
- Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation☆71Updated last year
- Jax/Flax Implementation of TD-MPC2☆62Updated 2 weeks ago
- The official implementation of flow Q-learning (FQL)☆158Updated 3 months ago
- A minimal and stable PPO.☆138Updated last year
- ☆102Updated 2 years ago
- ☆70Updated 3 years ago
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆161Updated last year
- Source files to replicate experiments in my ICLR 2022 paper.☆71Updated 11 months ago
- ☆92Updated last year
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆103Updated 2 months ago
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆131Updated last year