Агенты ИИ | AGI_and_RL

Multi-agent systems for quadcopters https://arxiv.org/abs/2101.00033

Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning h...

https://github.com/koulanurag/muzero-pytorch

Mastering Atari, Go, chess and shogi by planning with a learned modelwww.nature.com/articles/s41586-...

https://deepai.org/publication/semi-supervised-reward-learning-for-offline-reinforcement-learning

JAX MD: A Framework for Differentiable Physics https://github.com/google/jax-md

TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search https://papers.nips.cc/...

https://deepai.org/publication/gpu-accelerated-exhaustive-search-for-optimal-ensemble-of-black-box-o...

https://deepai.org/publication/efficient-reservoir-management-through-deep-reinforcement-learning

Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generationhttps...