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.
Clustered Reinforcement Learning
Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy
Estimating Risk and Uncertainty in Deep Reinforcement Learning
Distributional Reinforcement Learning for Efficient Exploration
Optimizing Routerless Network-on-Chip Designs: An Innovative Learning-Based Framework
The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
Concurrent Meta Reinforcement Learning
Learning Exploration Policies for Navigation
Bayesian Reinforcement Learning via Deep, Sparse Sampling
Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching
Information-Directed Exploration for Deep Reinforcement Learning
Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes
Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
Context-Dependent Upper-Confidence Bounds for Directed Exploration
Incentivizing Exploration with Selective Data Disclosure
DEEPGONET: Multi-label Prediction of GO Annotation for Protein from Sequence Using Cascaded Convolutional and Recurrent Network
Model-Based Active Exploration
Multi-Agent Fully Decentralized Value Function Learning with Linear Convergence Rates
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
Thompson Sampling Algorithms for Cascading Bandits
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning
Directed Exploration in PAC Model-Free Reinforcement Learning
Discovering Context Specific Causal Relationships
Count-Based Exploration with the Successor Representation
Optimization by Pairwise Linkage Detection, Incremental Linkage Set, and Restricted / Back Mixing: DSMGA-II
Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration
New/s/leak 2.0 - Multilingual Information Extraction and Visualization for Investigative Journalism
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes
Goal-oriented Trajectories for Efficient Exploration
Curiosity Driven Exploration of Learned Disentangled Goal Spaces
Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards
Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents
Meta-Learning for Stochastic Gradient MCMC
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.