Агенты ИИ | AGI_and_RL

QR-MIX: Distributional Value Function Factorisation for Cooperative Multi-Agent Reinforcement Learni...

Multi-Agent Collaboration via Reward Attribution Decomposition https://arxiv.org/abs/2010.08531

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning https://arx...

https://www.nature.com/articles/s41467-019-13073-w

https://github.com/arrival-ltd/catalyst-rl-tutorial

Human-Robot Collaboration via Deep Reinforcement Learning of Real-World Interactions https://arxiv.o...

Reinforcement Learning with Human Teachers: Evidence of Feedback andGuidance with Implications for L...

HILONet: Hierarchical Imitation Learning from Non-Aligned Observations https://arxiv.org/abs/2011.02...

https://ieeexplore.ieee.org/document/8594353

https://medium.com/pytorch/robotic-assembly-using-deep-reinforcement-learning-dfd9916c5ad7