{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"2006.05990","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","created":"2020-06-10","cited_by_count":162},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104},{"id":"2006.11751","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","created":"2020-06-21","cited_by_count":93},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58},{"id":"2101.07393","title":"Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning","created":"2021-01-19","cited_by_count":45},{"id":"1803.01118","title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","created":"2018-03-03","cited_by_count":44},{"id":"2101.11071","title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2021-01-26","cited_by_count":41},{"id":"1803.02811","title":"Accelerated Methods for Deep Reinforcement Learning","created":"2018-03-07","cited_by_count":40},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39},{"id":"2104.06272","title":"Podracer architectures for scalable Reinforcement Learning","created":"2021-04-13","cited_by_count":38},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36},{"id":"2012.08621","title":"BeBold: Exploration Beyond the Boundary of Explored Regions","created":"2020-12-15","cited_by_count":33},{"id":"2011.06363","title":"Griddly: A platform for AI research in games","created":"2020-11-12","cited_by_count":31},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20},{"id":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19},{"id":"2203.12117","title":"NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty","created":"2022-03-23","cited_by_count":14},{"id":"2308.13289","title":"JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading","created":"2023-08-25","cited_by_count":14},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10},{"id":"2206.00142","title":"IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents","created":"2022-05-31","cited_by_count":9},{"id":"1801.02852","title":"Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes","created":"2018-01-09","cited_by_count":6},{"id":"2006.07262","title":"A Brief Look at Generalization in Visual Meta-Reinforcement Learning","created":"2020-06-12","cited_by_count":5},{"id":"2306.08772","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","created":"2023-06-14","cited_by_count":5},{"id":"2311.00651","title":"Emergence of Collective Open-Ended Exploration from Decentralized Meta-Reinforcement Learning","created":"2023-11-01","cited_by_count":1}],"next_cursor":null}