{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138},{"id":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"1812.00971","title":"Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning","created":"2018-12-03","cited_by_count":93},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93},{"id":"2203.05701","title":"6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark","created":"2022-03-11","cited_by_count":86},{"id":"1706.07230","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","created":"2017-06-22","cited_by_count":72},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70},{"id":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67},{"id":"2101.05181","title":"Memory-Augmented Reinforcement Learning for Image-Goal Navigation","created":"2021-01-13","cited_by_count":66},{"id":"2011.08899","title":"Multimodal Prototypical Networks for Few-shot Learning","created":"2020-11-17","cited_by_count":48},{"id":"1909.01387","title":"Making Efficient Use of Demonstrations to Solve Hard Exploration Problems","created":"2019-09-03","cited_by_count":45},{"id":"1805.11240","title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","created":"2018-05-29","cited_by_count":39},{"id":"2103.13834","title":"Self-Imitation Learning by Planning","created":"2021-03-25","cited_by_count":26},{"id":"2007.00350","title":"Adaptive Procedural Task Generation for Hard-Exploration Problems","created":"2020-07-01","cited_by_count":20},{"id":"2110.05734","title":"Learning Efficient Multi-Agent Cooperative Visual Exploration","created":"2021-10-12","cited_by_count":19},{"id":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","cited_by_count":18},{"id":"2104.14040","title":"Pushing it out of the Way: Interactive Visual Navigation","created":"2021-04-28","cited_by_count":16},{"id":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13},{"id":"2006.07549","title":"Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning","created":"2020-06-13","cited_by_count":12},{"id":"2011.13467","title":"Episodic Self-Imitation Learning with Hindsight","created":"2020-11-26","cited_by_count":10},{"id":"2108.07887","title":"Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay","created":"2021-08-17","cited_by_count":7},{"id":"2110.12985","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","created":"2021-10-25","cited_by_count":7},{"id":"1901.11529","title":"Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs","created":"2019-01-31","cited_by_count":6},{"id":"1905.05498","title":"Bias-Reduced Hindsight Experience Replay with Virtual Goal Prioritization","created":"2019-05-14","cited_by_count":4},{"id":"2102.13008","title":"Imitation Learning with Human Eye Gaze via Multi-Objective Prediction","created":"2021-02-25","cited_by_count":4},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4},{"id":"2111.04345","title":"Off-policy Imitation Learning from Visual Inputs","created":"2021-11-08","cited_by_count":2},{"id":"2305.13741","title":"L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning","created":"2023-05-23","cited_by_count":2}],"next_cursor":null}