![End-to-End Deep Reinforcement Learning without Reward Engineering – The Berkeley Artificial Intelligence Research Blog End-to-End Deep Reinforcement Learning without Reward Engineering – The Berkeley Artificial Intelligence Research Blog](https://bair.berkeley.edu/static/blog/end_to_end/pr2_vice.gif)
End-to-End Deep Reinforcement Learning without Reward Engineering – The Berkeley Artificial Intelligence Research Blog
Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations
![Frontiers | From Semantics to Execution: Integrating Action Planning With Reinforcement Learning for Robotic Causal Problem-Solving | Robotics and AI Frontiers | From Semantics to Execution: Integrating Action Planning With Reinforcement Learning for Robotic Causal Problem-Solving | Robotics and AI](https://www.frontiersin.org/files/Articles/473936/frobt-06-00123-HTML/image_m/frobt-06-00123-g001.jpg)
Frontiers | From Semantics to Execution: Integrating Action Planning With Reinforcement Learning for Robotic Causal Problem-Solving | Robotics and AI
![Interactive Human–Robot Skill Transfer: A Review of Learning Methods and User Experience - Cansev - 2021 - Advanced Intelligent Systems - Wiley Online Library Interactive Human–Robot Skill Transfer: A Review of Learning Methods and User Experience - Cansev - 2021 - Advanced Intelligent Systems - Wiley Online Library](https://onlinelibrary.wiley.com/cms/asset/16c909fd-06c1-4e30-9818-ae26095c673e/aisy202000247-blkfxd-0001-m.jpg)
Interactive Human–Robot Skill Transfer: A Review of Learning Methods and User Experience - Cansev - 2021 - Advanced Intelligent Systems - Wiley Online Library
![Enhancing optical-flow-based control by learning visual appearance cues for flying robots | Nature Machine Intelligence Enhancing optical-flow-based control by learning visual appearance cues for flying robots | Nature Machine Intelligence](https://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs42256-020-00279-7/MediaObjects/42256_2020_279_Fig1_HTML.png)
Enhancing optical-flow-based control by learning visual appearance cues for flying robots | Nature Machine Intelligence
![Vision-based grasp learning of an anthropomorphic hand-arm system in a synergy-based control framework Vision-based grasp learning of an anthropomorphic hand-arm system in a synergy-based control framework](https://www.science.org/cms/10.1126/scirobotics.aao4900/asset/9b95d3e9-7390-4e4f-af35-eb98eca1eb31/assets/graphic/aao4900-f1.jpeg)