{"version":1,"pages":[{"id":"-MSZX5Chu04sZkgyntwC","title":"CS285: Deep RL Notes","pathname":"/deeprl-notes","siteSpaceId":"sitesp_6VAzK","description":""},{"id":"-MSZYDXbuPskpyCGq3M3","title":"RL Fundamentals","pathname":"/deeprl-notes/rl-fundamentals","siteSpaceId":"sitesp_6VAzK","description":"An introduction to core RL concepts"},{"id":"-MSZcvj26CGOhKpI6dz7","title":"Policy Gradient Basics","pathname":"/deeprl-notes/policy-gradient/policy-gradient-methods","siteSpaceId":"sitesp_6VAzK","description":"first of the three-part series on policy gradient methods","breadcrumbs":[{"label":"Policy Gradient"}]},{"id":"-MSZdJL8w5ze8Paq7lvI","title":"Actor Critic Algorithms","pathname":"/deeprl-notes/policy-gradient/actor-critic","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Policy Gradient"}]},{"id":"-MSZdSDYA-Lm0WgvH77K","title":"Advanced Policy Gradients","pathname":"/deeprl-notes/policy-gradient/advanced-policy-gradients","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Policy Gradient"}]},{"id":"-MSZcPprPPdWmq8Sd6CK","title":"Policy and Value Iteration Algorithms","pathname":"/deeprl-notes/value-based-methods-1/value-based-methods","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Value Based Methods"}]},{"id":"-MTEsm1TfD5g4A1WwZG_","title":"DQN and beyond","pathname":"/deeprl-notes/value-based-methods-1/dqn-and-beyond","siteSpaceId":"sitesp_6VAzK","description":"Q Learning that actually works :)","breadcrumbs":[{"label":"Value Based Methods"}]},{"id":"-MTF1kq3mDOyrqppJuq5","title":"Model-based Planning and Model-based Predictive Control","pathname":"/deeprl-notes/model-based-methods/model-based-planning-and-model-based-predictive-control","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Model-based Methods"}]},{"id":"-MSqT5rsVBUTLveauKTs","title":"Model-based Policy Learning","pathname":"/deeprl-notes/model-based-methods/untitled","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Model-based Methods"}]},{"id":"-MTF2CA5RtBqllqjui9H","title":"Latent Models and Variational Inference","pathname":"/deeprl-notes/inference-control-and-inverse-rl/latent-models-and-variational-inference","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Inference, Control, and Inverse RL"}]},{"id":"-MSqT9vpG5j6LowEnS6X","title":"Control as Inference","pathname":"/deeprl-notes/inference-control-and-inverse-rl/untitled","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Inference, Control, and Inverse RL"}]},{"id":"-MTF2VQKCJMxJM1O5fIB","title":"Inverse Reinforcement Learning","pathname":"/deeprl-notes/inference-control-and-inverse-rl/inverse-reinforcement-learning","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Inference, Control, and Inverse RL"}]},{"id":"-MSqTCqOlsznzz7AfHi8","title":"Transfer and Multi-task Learning","pathname":"/deeprl-notes/transfer-learning-in-rl/untitled","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Transfer Learning in RL"}]},{"id":"-MTIGShFX6dJ-iwnJRP1","title":"Paper Reading Notes","pathname":"/deeprl-notes/transfer-learning-in-rl/paper-reading-notes","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Transfer Learning in RL"}]},{"id":"-MTI6qlD-zaSk7Am7rAi","title":"Offline RL","pathname":"/deeprl-notes/coming-soon.../offline-rl","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Coming soon..."}]},{"id":"-MTI6vbSv1_cTdUQMovl","title":"RL from Pixels","pathname":"/deeprl-notes/coming-soon.../rl-from-pixels","siteSpaceId":"sitesp_6VAzK","description":"","breadcrumbs":[{"label":"Coming soon..."}]}]}