# Learning to Identify Critical States for Reinforcement Learning from Videos ## Summary Paper page for Learning to Identify Critical States for Reinforcement Learning from Videos. Published on Aug 15, 2023. Authors: Haozhe Liu, Mingchen Zhuge, Bing Li, Yuhui Wang, Francesco Faccio, Bernard Ghanem, Jürgen Schmidhuber. The paper introduces a method called Deep State Identifier that learns to predict returns from videos and extract critical states for reinforcement learning. Source code available on GitHub. ---- # Article # Learning to Identify Critical States for Reinforcement Learning from Videos Published on Aug 15, 2023 · Submitted by akhaliq on Aug 16, 2023 Authors: Haozhe Liu, Mingchen Zhuge, Bing Li, Yuhui Wang, Francesco Faccio, Bernard Ghanem, Jürgen Schmidhuber ## Abstract Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions. For example, videos of humans or robots may convey a lot of implicit information about rewarding action sequences, but a DRL machine that wants to profit from watching such videos must first learn by itself to identify and recognize relevant states/actions/rewards. Without relying on ground-truth annotations, our new method called Deep State Identifier learns to predict returns from episodes encoded as videos. Then it uses a kind of mask-based sensitivity analysis to extract/identify important critical states. Extensive experiments showcase our method's potential for understanding and improving agent behavior. The source code and the generated datasets are available at https://github.com/AI-Initiative-KAUST/VideoRLCS. [View arXiv page](https://arxiv.org/abs/2308.07795) [View PDF](https://arxiv.org/pdf/2308.07795) ## Community Comment Sign up or log in to comment ## Models citing this paper 0 No model linking this paper Cite arxiv.org/abs/2308.07795 in a model README.md to link it from this page. ## Datasets citing this paper 0 No dataset linking this paper Cite arxiv.org/abs/2308.07795 in a dataset README.md to link it from this page. ### Spaces citing this paper 0 No Space linking this paper Cite arxiv.org/abs/2308.07795 in a Space README.md to link it from this page. ## Collections including this paper 0 No Collection including this paper Add this paper to a collection to link it from this page.