InexperiencedMe / NaturalDreamer
Simplest and Cleanest DreamerV3 implementation out there
☆61Updated last month
Alternatives and similar repositories for NaturalDreamer:
Users that are interested in NaturalDreamer are comparing it to the libraries listed below
- Unified Implementations of Offline Reinforcement Learning Algorithms☆67Updated last week
- Simple single-file baselines for Q-Learning in pure-GPU setting☆161Updated last month
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆91Updated last month
- ☆82Updated 2 months ago
- ☆77Updated last month
- Challenging Memory-based Deep Reinforcement Learning Agents☆97Updated 6 months ago
- Highly scalable 2D JAX physics engine.☆56Updated last month
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"☆44Updated last week
- Goal-Conditioned Reinforcement Learning with JAX☆153Updated last week
- Clean single-file implementation of offline RL algorithms in JAX☆143Updated 4 months ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆205Updated last month
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning - - —☆68Updated 2 months ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆72Updated 8 months ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆22Updated 2 weeks ago
- ☆78Updated 6 months ago
- Efficient baselines for autocurricula in JAX.☆187Updated 8 months ago
- Code for the paper "Harnessing Discrete Representations for Continual Reinforcement Learning"☆14Updated 10 months ago
- ☆41Updated 9 months ago
- Accelerated minigrid environments with JAX☆135Updated 9 months ago
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆178Updated last month
- Foundation Policies with Hilbert Representations (ICML 2024)☆85Updated last year
- Reproduction of Dreamerv1 and v2 in pytorch for deepmind control suite☆38Updated 2 years ago
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆66Updated 11 months ago
- Synchronized Curriculum Learning for RL Agents☆44Updated last month
- a simple and scalable agent for training adaptive policies with sequence-based RL☆119Updated last week
- Jax/Flax Implementation of TD-MPC2☆61Updated last week
- An Open-Ended Agentic Simulator☆48Updated 8 months ago
- ☆72Updated last year
- JAX implementation of RL algorithms and vectorized environments☆43Updated last year
- Synthetic Experience Replay☆92Updated 11 months ago