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/shahab-k93/cancer-and-smart-nanorobot
공식 코드https://github.com/shahin-01/vqa-ad
공식 코드Explaining Autonomous Driving Actions with Visual Question Answering
https://github.com/shamanez/VUSFA-Variational-Universal-Successor-Features-Approximator
공식 코드https://github.com/shaneshixiang/rllabplusplus
공식 코드Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
https://github.com/shanest/function-words-context
공식 코드https://github.com/shangshang-wang/tina
공식 코드https://github.com/shanka123/llm_pfc
공식 코드Improving Planning with Large Language Models: A Modular Agentic Architecture
https://github.com/shanlior/ExplorationConsciousRL
공식 코드https://github.com/shaodaqian/rl-from-ltl
공식 코드https://github.com/sharadmv/parasol
공식 코드SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning
https://github.com/sharathraparthy/polynomial-mixing-times
공식 코드Continual Learning In Environments With Polynomial Mixing Times
https://github.com/sharif1093/dextron
공식 코드End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning
https://github.com/shariqiqbal2810/MAAC
공식 코드Actor-Attention-Critic for Multi-Agent Reinforcement Learning
https://github.com/shariqiqbal2810/Multi-Explore
공식 코드Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning
https://github.com/shariqiqbal2810/REFIL
공식 코드Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
https://github.com/sharkwyf/cgdt
공식 코드Critic-Guided Decision Transformer for Offline Reinforcement Learning
https://github.com/sharma1256/cbf-constrained_ppo
공식 코드Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
https://github.com/shashacks/irl_transition
공식 코드Training Transition Policies via Distribution Matching for Complex Tasks
https://github.com/shashacks/symmetric_rl
공식 코드Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
https://github.com/shashiongithub/Refresh
공식 코드Ranking Sentences for Extractive Summarization with Reinforcement Learning
https://github.com/shawnwun/NNDIAL
공식 코드https://github.com/shayantaherian/Vehicle-Stabilisation-Using-Reinforcement-Learning
공식 코드Self-adaptive Torque Vectoring Controller Using Reinforcement Learning
https://github.com/shayegano/CASL
공식 코드https://github.com/shehper/AC-Solver
공식 코드What makes math problems hard for reinforcement learning: a case study
https://github.com/shehryar-malik/icrl
공식 코드https://github.com/shengjiewang-jason/efficientzerov2
공식 코드EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
https://github.com/shengrenhou/drl-for-energy-systems-optimal-scheduling
공식 코드Performance Comparison of Deep RL Algorithms for Energy Systems Optimal Scheduling
https://github.com/shengzhang37/SAVE
공식 코드Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settings
https://github.com/shentao-yang/ampl_neurips2022
공식 코드A Unified Framework for Alternating Offline Model Training and Policy Learning
https://github.com/shentao-yang/fantastic_reward_iclr2023
공식 코드https://github.com/shentao-yang/sdm-gan_icml2022
공식 코드https://github.com/sherilan/cs285-project
공식 코드https://github.com/sherlock1987/SeqReward
공식 코드https://github.com/shiehshieh/fedkl
공식 코드FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence
https://github.com/shiehshieh/fedpohcs
공식 코드Client Selection for Federated Policy Optimization with Environment Heterogeneity
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.