{"id":"arxiv:2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","date":"2025-01-27","section":"Reinforcement learning","quality":-0.125258,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/","source_url":"https://arxiv.org/abs/2501.16142","text_available":true,"authors":["Scott Fujimoto","Pierluca D'Oro","Amy Zhang","Yuandong Tian"],"outgoing":[],"incoming":[],"text_parts":[{"start":0,"end":15708,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html"}],"contents":[{"title":"Towards General-Purpose Model-Free Reinforcement Learning","offset":0,"level":1,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"},{"title":"Abstract","offset":61,"level":6,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"},{"title":"1 Introduction","offset":1286,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"},{"title":"2 Related Work","offset":4973,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"},{"title":"3 Background","offset":9638,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"},{"title":"4 Model-based Representations for Q-learning","offset":10758,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"},{"title":"4.1 Theoretical Motivation","offset":13041,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"},{"title":"Instructions for reporting errors","offset":14744,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/part-1.html#text"}],"text_code_points":15708,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e9034f15fcd4385d96ab7cb30b3a0a011716ad52d13c7b87b84e17fb6e3398db/source.md"}