Keen-Technologies / physical_atariLinks
Platform for evaluating reinforcement learning (RL) algorithms on a physical Atari system.
☆141Updated 4 months ago
Alternatives and similar repositories for physical_atari
Users that are interested in physical_atari are comparing it to the libraries listed below
Sorting:
- ☆134Updated last month
- Cost aware hyperparameter tuning algorithm☆177Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆72Updated last year
- seqax = sequence modeling + JAX☆169Updated 5 months ago
- A simple, performant and scalable JAX-based world modeling codebase.☆122Updated this week
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆364Updated 6 months ago
- ☆288Updated last year
- A 3D video game environment and benchmark designed from scratch for reinforcement learning research☆190Updated 2 years ago
- ☆60Updated 6 months ago
- Efficient baselines for autocurricula in JAX.☆206Updated last year
- ☆176Updated last month
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆668Updated 4 months ago
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆226Updated last week
- ☆91Updated 4 months ago
- Dion optimizer algorithm☆419Updated this week
- Learn online intrinsic rewards from LLM feedback☆45Updated last year
- ☆213Updated 2 weeks ago
- Flax (Jax) implementation of DeepSeek-R1-Distill-Qwen-1.5B with weights ported from Hugging Face.☆26Updated 11 months ago
- SIMD quantization kernels☆93Updated 4 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆232Updated last month
- A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.☆135Updated this week
- A zero-to-one guide on scaling modern transformers with n-dimensional parallelism.☆113Updated 3 weeks ago
- MoE training for Me and You and maybe other people☆319Updated 2 weeks ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆115Updated last year
- The NetHack Learning Environment☆102Updated 3 weeks ago
- Implementation of Diffusion Transformer (DiT) in JAX☆305Updated last year
- Async RL Training at Scale☆1,005Updated this week
- ☆116Updated last week
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆131Updated 6 months ago
- Unified Implementations of Offline Reinforcement Learning Algorithms☆192Updated last month