{"id":"arxiv:2201.09746","title":"Reinforcement Learning Textbook","date":"2022-01-19","section":"Books","quality":-0.586946,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/","source_url":"https://arxiv.org/abs/2201.09746","text_available":true,"authors":["Sergey Ivanov"],"outgoing":[],"incoming":[],"text_parts":[{"start":0,"end":8536,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html"}],"contents":[{"title":"Конспект по обучению с подкреплением","offset":0,"level":1,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Задача обучения с подкреплением","offset":914,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Мета-эвристики","offset":3191,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Классическая теория","offset":3875,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Value-based подход","offset":4375,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Policy Gradient подход","offset":4861,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Continuous control","offset":5433,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Model-based","offset":5882,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Next Stage","offset":6140,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Приложение","offset":7456,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"},{"title":"Instructions for reporting errors","offset":7572,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/part-1.html#text"}],"text_code_points":8536,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/858e0104d53b9ae09818c743578349bb5385c3aed320640a292c13f01ea5b6d8/source.md"}