https://github.com/mikelma/craftium
공식 코드Craftium: An Extensible Framework for Creating Reinforcement Learning Environments
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/mikezhang95/HDNO
공식 코드https://github.com/mikezhang95/rrl_usr
공식 코드Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization
https://github.com/mila-iqia/SGI
공식 코드Pretraining Representations for Data-Efficient Reinforcement Learning
https://github.com/mila-iqia/babyai
공식 코드https://github.com/mila-iqia/casande-rl
공식 코드https://github.com/mila-iqia/conscious-planning
공식 코드A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
https://github.com/mila-iqia/spr
공식 코드Data-Efficient Reinforcement Learning with Self-Predictive Representations
https://github.com/minaek/reward_design_with_llms
공식 코드https://github.com/ming93/Safe_reinforcement_learning
공식 코드Convergent Policy Optimization for Safe Reinforcement Learning
https://github.com/mingkaid/rl-prompt
공식 코드RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
https://github.com/minglllli/CLS-RL
공식 코드Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning
https://github.com/mingyucai/E-LDGBA_RL
공식 코드Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction
https://github.com/mingyucai/Modular_Deep_RL_E-LDGBA
공식 코드Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic
https://github.com/minimax-ai/minimax-m1
공식 코드MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
https://github.com/minimax-ai/synlogic
공식 코드SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
https://github.com/minimaxbrl/minimax-bayes-rl
공식 코드https://github.com/minnesotanlp/dynamic-multi-reward-weighting
공식 코드Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation
https://github.com/minori5214/rl-guided-didp
공식 코드Reinforcement Learning-based Heuristics to Guide Domain-Independent Dynamic Programming
https://github.com/minqi/wordcraft
공식 코드WordCraft: An Environment for Benchmarking Commonsense Agents
https://github.com/minusadd/vblrl
공식 코드Model-based Lifelong Reinforcement Learning with Bayesian Exploration
https://github.com/miralab-ustc/rl-cbm
공식 코드https://github.com/miralab-ustc/rl-cresp
공식 코드https://github.com/miryoosefi/ConRL
공식 코드Constrained episodic reinforcement learning in concave-convex and knapsack settings
https://github.com/mit-acl/gym-collision-avoidance
공식 코드Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning
https://github.com/mit-acl/nn_robustness_analysis
공식 코드https://github.com/mit-wu-lab/IntersectionZoo
공식 코드IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning
https://github.com/mit-wu-lab/automatic_vehicular_control
공식 코드Unified Automatic Control of Vehicular Systems with Reinforcement Learning
https://github.com/mitkina/EnvironmentPrediction
공식 코드https://github.com/miulab/aisysopt-survey
공식 코드Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions
https://github.com/mixarcid/molucinate
공식 코드https://github.com/mjysh/RL3linkFish
공식 코드https://github.com/mklissa/dceo
공식 코드Deep Laplacian-based Options for Temporally-Extended Exploration
https://github.com/mklissa/moc
공식 코드https://github.com/ml-jku/OfflineRL
공식 코드https://github.com/ml-jku/RA-DT
공식 코드Retrieval-Augmented Decision Transformer: External Memory for In-context RL
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.