Papers with Code 아카이브
Efficient Exploration
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.
Source: Randomized Value Functions via Multiplicative Normalizing Flows
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/bhyang/diffusion-es
공식 코드https://github.com/brucegeli/top_erl_iclr25
공식 코드TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
https://github.com/buaawgj/lope
공식 코드Preference-Guided Reinforcement Learning for Efficient Exploration
https://github.com/caisr-hh/combineuserenvironment
공식 코드A New Bandit Setting Balancing Information from State Evolution and Corrupted Context
https://github.com/chandar-lab/coe
공식 코드Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning
https://github.com/chengqiarchy/mermaidflow
공식 코드MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
https://github.com/cl2-uwaterloo/genplan
공식 코드https://github.com/core-robotics-lab/opponent-modeling
공식 코드Diffusion-Reinforcement Learning Hierarchical Motion Planning in Multi-agent Adversarial Games
https://github.com/cyberagentailab/webcolor
공식 코드https://github.com/da-molchanov/variance-networks
공식 코드Variance Networks: When Expectation Does Not Meet Your Expectations
https://github.com/danilprov/cmdp
공식 코드An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning
https://github.com/diffusionyes/maxentdp
공식 코드Maximum Entropy Reinforcement Learning with Diffusion Policy
https://github.com/ehtesam3154/inhrecon
공식 코드Feature Interaction Aware Automated Data Representation Transformation
https://github.com/ejokhan/transnas_tsad
공식 코드https://github.com/enuzhin/ur
공식 코드Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems
https://github.com/ethz-asl/ssc_exploration
공식 코드SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning
https://github.com/facebookresearch/OccupancyAnticipation
공식 코드Occupancy Anticipation for Efficient Exploration and Navigation
https://github.com/facebookresearch/TCDM
공식 코드Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps
https://github.com/facebookresearch/hsd3
공식 코드https://github.com/facebookresearch/online-dt
공식 코드https://github.com/flowersteam/Curiosity_Driven_Goal_Exploration
공식 코드Curiosity Driven Exploration of Learned Disentangled Goal Spaces
https://github.com/flowersteam/curious
공식 코드CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
https://github.com/flowersteam/holmes
공식 코드Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems
https://github.com/garywei944/chemflow
공식 코드https://github.com/genentech/perturbqa
공식 코드Contextualizing biological perturbation experiments through language
https://github.com/gpaolo/stax
공식 코드Discovering and Exploiting Sparse Rewards in a Learned Behavior Space
https://github.com/henriTUD/musculoco_learning
공식 코드https://github.com/hmishfaq/lmc-lsvi
공식 코드Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
https://github.com/hmishfaq/lsac
공식 코드Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
https://github.com/htdt/lwm
공식 코드https://github.com/hugorichard/ml4a-scheduling
공식 코드https://github.com/ianwhale/nsga-net
공식 코드NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
https://github.com/icitylab/hspr
공식 코드Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation
https://github.com/ihuhuhu/RAC
공식 코드Balancing Value Underestimation and Overestimation with Realistic Actor-Critic
https://github.com/imanolarrieta/angrybirds
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.