{"id":"arxiv:2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","date":"2023-06-04","section":"Reinforcement learning","quality":0.048804,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/","source_url":"https://arxiv.org/abs/2306.02451","text_available":true,"authors":["Scott Fujimoto","Wei-Di Chang","Edward J. Smith","Shixiang Shane Gu"],"outgoing":[{"source":"arxiv:2306.02451","target":"arxiv:1511.05952","evidence":"title","id":"arxiv:1511.05952","title":"Prioritized Experience Replay","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c88bf0c11c1817dcc457c001dfef5cd120a0946c8a009a0fe40648dae03eb7d4/"}],"incoming":[],"text_parts":[{"start":0,"end":15812,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html"},{"start":15812,"end":26194,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-2.html"},{"start":26194,"end":42194,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-3.html"},{"start":42194,"end":43864,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-4.html"}],"contents":[{"title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","offset":0,"level":1,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html#text"},{"title":"Abstract","offset":82,"level":6,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html#text"},{"title":"1 Introduction","offset":971,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html#text"},{"title":"2 Related Work","offset":4913,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html#text"},{"title":"3 Background","offset":8242,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html#text"},{"title":"4 State-Action Representation Learning","offset":9097,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html#text"},{"title":"4.1 State-Action Learned Embeddings","offset":9507,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-1.html#text"},{"title":"4.2 Evaluating Design Choices","offset":17640,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-2.html#text"},{"title":"5 Stabilizing RL with Decoupled Representation Learning","offset":21272,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-2.html#text"},{"title":"5.1 Policy Checkpoints","offset":21684,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-2.html#text"},{"title":"5.2 TD7","offset":25173,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/part-2.html#text"}],"text_code_points":43864,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/952e0e96fff2857b76e6b62a24d57ca4f6ac86ad8e8a21cb4d31a4dc051f8885/source.md"}