Papers with Code 아카이브
Reinforcement Learning (RL)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 2
- 보존된 평가 기록
- 3
Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/NUS-LID/RENAULT
공식 코드Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning
https://github.com/NVIDIA-Omniverse/IsaacGymEnvs
공식 코드DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality
https://github.com/NVIDIA-Omniverse/Orbit
공식 코드Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments
https://github.com/NVIDIA/GraphQSat
공식 코드Can $Q$-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?
https://github.com/NVLABs/cule
공식 코드Accelerating Reinforcement Learning through GPU Atari Emulation
https://github.com/NVlabs/GA3C
공식 코드Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
https://github.com/NVlabs/bayes-sim-ig
공식 코드BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym
https://github.com/NVlabs/unas
공식 코드UNAS: Differentiable Architecture Search Meets Reinforcement Learning
https://github.com/NYCU-RL-Bandits-Lab/Q-Pensieve
공식 코드Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
https://github.com/NagisaZj/MetaCURE-Public
공식 코드MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
https://github.com/Nardien/NMG
공식 코드Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation
https://github.com/NeteaseFuxiRL/action-balance-exploration
공식 코드https://github.com/Networks-Learning/tpprl
공식 코드Deep Reinforcement Learning of Marked Temporal Point Processes
https://github.com/NeuroCSUT/DeepMind-Atari-Deep-Q-Learner-2Player
공식 코드Multiagent Cooperation and Competition with Deep Reinforcement Learning
https://github.com/NeuroCSUT/intentions
공식 코드https://github.com/NevVerVer/DBS-Gym
공식 코드https://github.com/NiMlr/High-Dim-ES-RL
공식 코드Challenges in High-dimensional Reinforcement Learning with Evolution Strategies
https://github.com/Nick-Kou/RL-PGO
공식 코드RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization
https://github.com/NikeHop/CSRL
공식 코드https://github.com/Nikunj-Gupta/HAMMER
공식 코드HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging
https://github.com/NinaMaz/NAS_RL_torch
공식 코드Optimizing the Neural Architecture of Reinforcement Learning Agents
https://github.com/Nirnai/DeepRL
공식 코드https://github.com/Nordeus/heroic-rl
공식 코드https://github.com/OamIcs/MoSim
공식 코드Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
https://github.com/Ojig/Environment-Design-for-IRL
공식 코드https://github.com/OliverRichter/map-reader
공식 코드Teaching a Machine to Read Maps with Deep Reinforcement Learning
https://github.com/OmarErak/LLM-CL
공식 코드Large Language Model-Driven Curriculum Design for Mobile Networks
https://github.com/OpenLLMAI/OpenRLHF
공식 코드Aligning Language Models with Offline Learning from Human Feedback
https://github.com/OpenRL-Lab/DGPO
공식 코드DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
https://github.com/OptiMaL-PSE-Lab/CIRL
공식 코드Control-Informed Reinforcement Learning for Chemical Processes
https://github.com/OptimalPursuit/navigating_uncertainty_in_mpp
공식 코드https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari
공식 코드Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration
https://github.com/Owen-Oertell/rlcm
공식 코드RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
https://github.com/PAL-ML/PEARL_v1
공식 코드https://github.com/PKU-AI-Edge/DGN
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.