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.
Hybrid Genetic Search for the CVRP: Open-Source Implementation and SWAP* Neighborhood
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization
A New Bandit Setting Balancing Information from State Evolution and Corrupted Context
Hierarchical reinforcement learning for efficient exploration and transfer
Amortized Variational Deep Q Network
Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning
Efficient Robotic Object Search via HIEM: Hierarchical Policy Learning with Intrinsic-Extrinsic Modeling
Deep Learning based Uncertainty Decomposition for Real-time Control
Latent World Models For Intrinsically Motivated Exploration
Efficient, Decentralized, and Collaborative Multi-Robot Exploration using Optimal Transport Theory
Novelty Search in Representational Space for Sample Efficient Exploration
SEMI: Self-supervised Exploration via Multisensory Incongruity
PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning
Occupancy Anticipation for Efficient Exploration and Navigation
DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the Loop
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads
See, Hear, Explore: Curiosity via Audio-Visual Association
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems
End-Effect Exploration Drive for Effective Motor Learning
Task-agnostic Exploration in Reinforcement Learning
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
From proprioception to long-horizon planning in novel environments: A hierarchical RL model
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
Multirobot Coverage of Modular Environments
PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning
Bayesian optimisation of large-scale photonic reservoir computers
Weakly-Supervised Reinforcement Learning for Controllable Behavior
Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning
Active Model Estimation in Markov Decision Processes
Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path
Scaling MAP-Elites to Deep Neuroevolution
Optimistic Exploration even with a Pessimistic Initialisation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.