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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
GFlowNets for AI-Driven Scientific Discovery
Computational Discovery of Microstructured Composites with Optimal Stiffness-Toughness Trade-Offs
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
Embodied Agents for Efficient Exploration and Smart Scene Description
Exploration in Model-based Reinforcement Learning with Randomized Reward
Strangeness-driven Exploration in Multi-Agent Reinforcement Learning
SHIRO: Soft Hierarchical Reinforcement Learning
Generative Colorization of Structured Mobile Web Pages
Reinforcement Learning in Credit Scoring and Underwriting
Efficient Exploration in Resource-Restricted Reinforcement Learning
Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning
CURO: Curriculum Learning for Relative Overgeneralization
HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression
Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions
CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control
Efficient Exploration using Model-Based Quality-Diversity with Gradients
Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation
Exploring through Random Curiosity with General Value Functions
Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction
Design of Convolutional Extreme Learning Machines for Vision-Based Navigation Around Small Bodies
GeoThermalCloud: Machine Learning for Geothermal Resource Exploration
LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward
Deep Active Ensemble Sampling For Image Classification
The Role of Coverage in Online Reinforcement Learning
Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps
Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning
An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning
SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning
Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
The split Gibbs sampler revisited: improvements to its algorithmic structure and augmented target distribution
GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation
A Langevin-like Sampler for Discrete Distributions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.