{"total":30,"papers":[{"id":"arxiv:2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","date":"2025-03-19","section":"Reinforcement learning","quality":0.017695,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/dfa04045239215a4a49544cd31c178090abc3a587e98bd9af08e0ea96d658911/","source_url":"https://arxiv.org/abs/2503.14858","text_available":true},{"id":"arxiv:1707.06887","title":"A Distributional Perspective on Reinforcement Learning","date":"2017-07-21","section":"Reinforcement learning","quality":0.349015,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/96b040bb771d28ca3254b5519a2191c3e958a35dfdd60075344ac86af6a590e1/","source_url":"https://arxiv.org/abs/1707.06887","text_available":true},{"id":"arxiv:2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","date":"2021-06-12","section":"Reinforcement learning","quality":-0.495051,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/00a35c7a58d8775f23035efbd1cb0a5f540440d47b8a996be8a4fa0da2da3e0e/","source_url":"https://arxiv.org/abs/2106.06860","text_available":true},{"id":"arxiv:1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","section":"Reinforcement learning","quality":-0.361532,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5d1a410c86d85da493735fae67eb1b2689350e5ac449d39717deafaf3904e7c1/","source_url":"https://arxiv.org/abs/1802.09477","text_available":true},{"id":"arxiv:1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","date":"2019-10-03","section":"Reinforcement learning","quality":-0.5589,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ce9cb9b764eb7fdaf1aa766cb24e6abaec20a00445ad5af5a6dacb5af3ad3ddc/","source_url":"https://arxiv.org/abs/1910.01708","text_available":true},{"id":"arxiv:2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","date":"2024-11-06","section":"Reinforcement learning","quality":0.211995,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8bcc96ef608c017d3ddb7ded7dc9e3b760390f7df441214eeee08a2586c981ea/","source_url":"https://arxiv.org/abs/2411.03820","text_available":true},{"id":"arxiv:2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","date":"2023-05-30","section":"Reinforcement learning","quality":0.228173,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/727a7ee43fd005401d34d4591a2f49d85175f9366ebf2c9e7a862b340787614e/","source_url":"https://arxiv.org/abs/2305.19452","text_available":true},{"id":"arxiv:2509.09675","title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models","date":"2025-09-11","section":"Reinforcement learning","quality":0.1136,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f5581044978796ff7f35cb68c27963d3abbb391d35d88173ff7801242cbb1f7a/","source_url":"https://arxiv.org/abs/2509.09675","text_available":true},{"id":"arxiv:1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","date":"2017-12-18","section":"Reinforcement learning","quality":0.395745,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7191dc11e224beb3dc9abb8cd4efc58c70b79939b61fd56e4416b4b5e1404312/","source_url":"https://arxiv.org/abs/1712.06567","text_available":true},{"id":"arxiv:1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","section":"Reinforcement learning","quality":0.079916,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a2f115ac879cd2efb9548baf3ecdcb925d2492f03b4b0940720f6e5b0840715b/","source_url":"https://arxiv.org/abs/1509.06461","text_available":true},{"id":"url:diamond-wm.github.io","title":"Diffusion for World Modeling: Visual Details Matter in Atari","date":"2024-05-20","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c30654641002c1bf51b73571279dc615b5e9c5eeb1270df69b46cc0f5b0536ae/","source_url":"https://diamond-wm.github.io/","text_available":false},{"id":"arxiv:1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","section":"Reinforcement learning","quality":0.086863,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0a5f0593cf943c782ba38ae2fc386f953f859b9d3fc9722e8f17f67ca9cf50b5/","source_url":"https://arxiv.org/abs/1511.06581","text_available":true},{"id":"arxiv:2004.12919","title":"First return, then explore","date":"2020-04-27","section":"Reinforcement learning","quality":0.582832,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3cd790c501eaa633193918533947c58e30d1939bc08577606f1d88c56d368285/","source_url":"https://arxiv.org/abs/2004.12919","text_available":true},{"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},{"id":"arxiv:2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","date":"2023-12-20","section":"Reinforcement learning","quality":-0.055241,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/03e08bdf5d5c670f49cce235ed39b6ddb047bc31370ae7d24b68d13f81e232f6/","source_url":"https://arxiv.org/abs/2312.13327","text_available":true},{"id":"arxiv:2301.04104","title":"Mastering Diverse Domains through World Models","date":"2023-01-10","section":"Reinforcement learning","quality":0.159126,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/266d59e63d2f705efdc2eb7ad93f5126b7092b4450efd0d8c17099c51574b176/","source_url":"https://arxiv.org/abs/2301.04104","text_available":true},{"id":"arxiv:2312.00276","title":"Metalearning Continual Learning Algorithms","date":"2023-12-01","section":"Reinforcement learning","quality":0.12499,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5d7361f404c0455d9f759fc6a8dd7bd1da75146e72717b7a2fbcdb8bac80412a/","source_url":"https://arxiv.org/abs/2312.00276","text_available":true},{"id":"arxiv:2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","date":"2020-05-04","section":"Reinforcement learning","quality":-0.419453,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2ae228e6f0a418b4cd46f033b57c7452ba84a9c8cb985b198224186333c17d97/","source_url":"https://arxiv.org/abs/2005.01643","text_available":true},{"id":"arxiv:1511.05952","title":"Prioritized Experience Replay","date":"2015-11-18","section":"Reinforcement learning","quality":-0.008072,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c88bf0c11c1817dcc457c001dfef5cd120a0946c8a009a0fe40648dae03eb7d4/","source_url":"https://arxiv.org/abs/1511.05952","text_available":true},{"id":"arxiv:2608.17163","title":"Q-Learning With World Models","date":"2026-08-17","section":"Reinforcement learning","quality":0.08444,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/15ca8843297a713249e241e591505a44859dac258c54e299d79c62c81bd893c2/","source_url":"https://arxiv.org/abs/2608.17163","text_available":true},{"id":"arxiv:1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","section":"Reinforcement learning","quality":-0.054363,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4183a5aecdb6558733bd0b2028e6197904c8b46173181bf6c8270fb6cbcfc973/","source_url":"https://arxiv.org/abs/1710.02298","text_available":true},{"id":"arxiv:2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","date":"2020-11-20","section":"Reinforcement learning","quality":-0.269176,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2bf20803a5d9e686543fe5f3967e69b5aa481ba29ff91c9ca3fbeb147ab8c0aa/","source_url":"https://arxiv.org/abs/2011.14826","text_available":true},{"id":"openreview:OpC-9aBBVJe","title":"Sample-Efficient RL by Breaking the Replay Ratio Barrier (ICLR 2023, precursor of BBF)","date":"2022-09-28","section":"Reinforcement learning","quality":0.161355,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8bab1f9ee93a0613f60e3e9577b9ddcad6937e59c156709d0351478c38f1d5bf/","source_url":"https://openreview.net/forum?id=OpC-9aBBVJe","text_available":true},{"id":"arxiv:2602.06130","title":"Self-Improving World Modelling with Latent Actions","date":"2026-02-05","section":"Reinforcement learning","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/ac56340e6b81e232b48b92dcf79fe37efc1c00e676413e55c9d119a809eb644b/","source_url":"https://arxiv.org/abs/2602.06130","text_available":true}],"next":"https://vinnik-dmitry07.github.io/favorite-papers/agents/catalog-1-2.html"}