{"total":30,"papers":[{"id":"arxiv:1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","section":"Reinforcement learning","quality":0.455513,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/21e70876ae9603903b2b20dd667a413bdd8b0abf37b9c11e284ea8b5e4124c74/","source_url":"https://arxiv.org/abs/1801.01290","text_available":true},{"id":"url:lilianweng.github.io/lil-log/2018/01/23/the-multi-armed-bandit-problem-and-its-solutions.html","title":"The Multi-Armed Bandit Problem and Its Solutions (Lilian Weng)","date":"2018-01-23","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/24db6186104ad4deb9b8cf44d92e009bc23dc6d50c9467ff1d5b3745e2babd0b/","source_url":"https://lilianweng.github.io/lil-log/2018/01/23/the-multi-armed-bandit-problem-and-its-solutions.html","text_available":false},{"id":"arxiv:2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","date":"2022-05-16","section":"Reinforcement learning","quality":0.266696,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4e2aca370b941bb16bb6fefc359c420f6d4bde5a956bedaf0a84e6e71febc5bc/","source_url":"https://arxiv.org/abs/2205.07802","text_available":true},{"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},{"id":"arxiv:2211.10869","title":"UniMASK: Unified Inference in Sequential Decision Problems","date":"2022-11-20","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/919bff55efff4ed3549bd106b843afa3d140b32938f5283c77821d7fd569452e/","source_url":"https://arxiv.org/abs/2211.10869","text_available":true},{"id":"openreview:XyGJJ4FPoX","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","date":"2022-10-01","section":"Reinforcement learning","quality":-0.454643,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/fb4e3bd06740741f593887b474deedc44ad341fa5736c2970e3cc11f065d58de/","source_url":"https://openreview.net/forum?id=XyGJJ4FPoX","text_available":true}],"next":null}