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.
Balancing Value Underestimation and Overestimation with Realistic Actor-Critic
Efficient Exploration in Binary and Preferential Bayesian Optimization
Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization
Reinforcement Learning in Reward-Mixing MDPs
Exploring More When It Needs in Deep Reinforcement Learning
Exploratory State Representation Learning
Differentially Evolving Memory Ensembles: Pareto Optimization based on Computational Intelligence for Embedded Memories on a System Level
Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge
Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
Bootstrapped Meta-Learning
A Gradient Sampling Algorithm for Stratified Maps with Applications to Topological Data Analysis
Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning
Learn2Hop: Learned Optimization on Rough Landscapes
Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning
MADE: Exploration via Maximizing Deviation from Explored Regions
Impact of detecting clinical trial elements in exploration of COVID-19 literature
Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning
Principled Exploration via Optimistic Bootstrapping and Backward Induction
Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks
Paradiseo: From a Modular Framework for Evolutionary Computation to the Automated Design of Metaheuristics ---22 Years of Paradiseo---
MAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Cores
Behavior-Guided Actor-Critic: Improving Exploration via Learning Policy Behavior Representation for Deep Reinforcement Learning
Nonlinear model reduction for slow-fast stochastic systems near unknown invariant manifolds
Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure
Learning Memory-Dependent Continuous Control from Demonstrations
State Entropy Maximization with Random Encoders for Efficient Exploration
Meta-Thompson Sampling
Adversarially Guided Actor-Critic
Online Limited Memory Neural-Linear Bandits with Likelihood Matching
Sparse Reward Exploration via Novelty Search and Emitters
The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors
Autonomous synthesis of metastable materials
Robotic Grasping of Fully-Occluded Objects using RF Perception
Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning
BeBold: Exploration Beyond the Boundary of Explored Regions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.