{"cited_by_count":1236823,"description":"This cluster of papers encompasses a wide range of advancements in reinforcement learning algorithms and their applications, including deep learning, neural networks, robotics, autonomous control, policy gradient methods, multi-agent systems, model-based learning, curiosity-driven exploration, and simulation to real-world transfer.","display_name":"Reinforcement Learning in Robotics","domain_id":"3","external_ids":{"openalex":"https://openalex.org/T10462","wikipedia":"https://en.wikipedia.org/wiki/Reinforcement_learning"},"field_id":"17","id":"T10462","keywords":[{"display_name":"multi-agent reinforcement learning","id":"multi-agent-reinforcement-learning","score":0.3766,"url":"https://openalex.org/keywords/multi-agent-reinforcement-learning"},{"display_name":"sample efficiency","id":"sample-efficiency","score":0.5842,"url":"https://openalex.org/keywords/sample-efficiency"},{"display_name":"Q-learning","id":"q-learning","score":0.2449,"url":"https://openalex.org/keywords/q-learning"},{"display_name":"imitation learning","id":"imitation-learning","score":0.3056,"url":"https://openalex.org/keywords/imitation-learning"},{"display_name":"model-based reinforcement learning","id":"model-based-reinforcement-learning","score":0.7035,"url":"https://openalex.org/keywords/model-based-reinforcement-learning"},{"display_name":"proximal policy optimization","id":"proximal-policy-optimization","score":0.2485,"url":"https://openalex.org/keywords/proximal-policy-optimization"},{"display_name":"sparse rewards","id":"sparse-rewards","score":0.7576,"url":"https://openalex.org/keywords/sparse-rewards"},{"display_name":"reward function design","id":"reward-function-design","score":0.2516,"url":"https://openalex.org/keywords/reward-function-design"},{"display_name":"offline reinforcement learning","id":"offline-reinforcement-learning","score":0.7108,"url":"https://openalex.org/keywords/offline-reinforcement-learning"},{"display_name":"sim-to-real transfer","id":"sim-to-real-transfer","score":0.4455,"url":"https://openalex.org/keywords/sim-to-real-transfer"},{"display_name":"robot learning","id":"robot-learning","score":0.3877,"url":"https://openalex.org/keywords/robot-learning"},{"display_name":"partially observable Markov decision processes","id":"partially-observable-markov-decision-processes","score":0.2881,"url":"https://openalex.org/keywords/partially-observable-markov-decision-processes"},{"display_name":"continuous control","id":"continuous-control","score":0.6149,"url":"https://openalex.org/keywords/continuous-control"},{"display_name":"hierarchical reinforcement learning","id":"hierarchical-reinforcement-learning","score":0.5037,"url":"https://openalex.org/keywords/hierarchical-reinforcement-learning"},{"display_name":"deep deterministic policy gradient","id":"ddpg","score":0.2325,"url":"https://openalex.org/keywords/ddpg"},{"display_name":"actor-critic","id":"actor-critic","score":0.3976,"url":"https://openalex.org/keywords/actor-critic"},{"display_name":"temporal difference learning","id":"temporal-difference-learning","score":0.5398,"url":"https://openalex.org/keywords/temporal-difference-learning"},{"display_name":"model-free reinforcement learning","id":"model-free-reinforcement-learning","score":0.4777,"url":"https://openalex.org/keywords/model-free-reinforcement-learning"},{"display_name":"policy gradient","id":"policy-gradient","score":0.4802,"url":"https://openalex.org/keywords/policy-gradient"},{"display_name":"reward shaping","id":"reward-shaping","score":0.5364,"url":"https://openalex.org/keywords/reward-shaping"},{"display_name":"policy optimization","id":"policy-optimization","score":0.4396,"url":"https://openalex.org/keywords/policy-optimization"},{"display_name":"soft actor-critic","id":"soft-actor-critic","score":0.3169,"url":"https://openalex.org/keywords/soft-actor-critic"},{"display_name":"inverse reinforcement learning","id":"inverse-reinforcement-learning","score":0.5393,"url":"https://openalex.org/keywords/inverse-reinforcement-learning"},{"display_name":"off-policy learning","id":"off-policy-learning","score":0.6313,"url":"https://openalex.org/keywords/off-policy-learning"},{"display_name":"world models","id":"world-models","score":0.2164,"url":"https://openalex.org/keywords/world-models"}],"legacy_keywords":["Reinforcement Learning","Deep Learning","Neural Networks","Robotics","Autonomous Control","Policy Gradient","Multi-Agent Systems","Model-Based Learning","Curiosity-Driven Exploration","Simulation to Real-world Transfer"],"openalex_id":"https://openalex.org/T10462","source_created_date":"2024-01-23T15:27:06","source_updated_date":"2026-10-17T03:02:00","subfield_id":"1702","url":"/topics/T10462","works_api_url":"https://api.openalex.org/works?filter=topics.id:T10462","works_count":93655,"label":"Reinforcement Learning in Robotics","provider":"openalex","revision":"efe0acbf00a56b1f","taxonomy_revision":"f050b5d4780b1289","title":"Reinforcement Learning in Robotics","kind":"topic-directory","aeo_cohort":"topic-directory","catalogue_revision":"f050b5d4780b1289","numeric_address":"36174210792066259","address_version":"morton4x16-v1","coordinates":[3,17,1702,10462],"answer_status":"Directory metadata; local answer requires separate source review","truth_status":"Subject descriptor, not a factual answer or a demonstrated knowledge gap","reviewed_answer":null}