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/vwxyzjn/action-guidance
공식 코드Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games
https://github.com/vwxyzjn/cleanrl
공식 코드CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms
https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/rpo_continuous_action.py
공식 코드https://github.com/vwxyzjn/gym-microrts
공식 코드Comparing Observation and Action Representations for Deep Reinforcement Learning in $μ$RTS
https://github.com/vwxyzjn/gym-microrts-paper
공식 코드https://github.com/vzhong/language-dynamics-distillation
공식 코드Improving Policy Learning via Language Dynamics Distillation
https://github.com/w2sr-neurips/code
공식 코드https://github.com/wadiuvatzy/sam-g
공식 코드Generalizable Visual Reinforcement Learning with Segment Anything Model
https://github.com/wadx2019/qvpo
공식 코드Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
https://github.com/wadx2019/rpo
공식 코드Reduced Policy Optimization for Continuous Control with Hard Constraints
https://github.com/walleclipse/reinforcement-learning-pulse-stacking
공식 코드An Optical Control Environment for Benchmarking Reinforcement Learning Algorithms
https://github.com/waltonfuture/mm-upt
공식 코드Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO
https://github.com/waltonfuture/rl-with-cold-start
공식 코드Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
https://github.com/wangclnlp/DeepSpeed-Chat-Extension/tree/main/examples/esrl
공식 코드ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
https://github.com/wanghanlinhenry/spa-rl-agent
공식 코드SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution
https://github.com/wangjksjtu/peerpl
공식 코드https://github.com/wangjksjtu/rl-perturbed-reward
공식 코드https://github.com/wangjs9/aligned-dpm
공식 코드Aligning Language Models with Human Preferences via a Bayesian Approach
https://github.com/wangleiphy/VAN.jl
공식 코드Solving Statistical Mechanics Using Variational Autoregressive Networks
https://github.com/wangyuhuix/TRGPPO
공식 코드https://github.com/wangyuhuix/TRPPO
공식 코드https://github.com/wantbook-book/serl
공식 코드SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data
https://github.com/waterhorse1/natural-language-rl
공식 코드https://github.com/watermeleon/RL_for_imbalanced_classification
공식 코드Balancing the Scales: Reinforcement Learning for Fair Classification
https://github.com/watermeloncq/drl-long-short-optimization-portfolio-SB3py37
공식 코드Deep Reinforcement Learning for Long-Short Portfolio Optimization
https://github.com/watml/min-max-2nd-order
공식 코드https://github.com/wayrise/dexgarmentlab
공식 코드DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy
https://github.com/wbarfuss/intrinsic-fluctuations-cooperation
공식 코드Intrinsic fluctuations of reinforcement learning promote cooperation
https://github.com/wcarvalho/farm
공식 코드Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning
https://github.com/wcgcyx/sac-cepo
공식 코드https://github.com/wdphy16/stat-mech-van
공식 코드Solving Statistical Mechanics Using Variational Autoregressive Networks
https://github.com/webbah/sec-for-reinforcement-learning
공식 코드https://github.com/weichenli1223/text-based-adventure-games-using-sac
공식 코드Learning to Play Text-based Adventure Games with Maximum Entropy Reinforcement Learning
https://github.com/weifantt/AutoFS
공식 코드AutoFS: Automated Feature Selection via Diversity-aware Interactive Reinforcement Learning
https://github.com/weihaotan/twosome
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.