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.
Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems
On Preemption and Learning in Stochastic Scheduling
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
Personalized Algorithmic Recourse with Preference Elicitation
Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration
SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning
The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure
Feature and Instance Joint Selection: A Reinforcement Learning Perspective
On Machine Learning-Driven Surrogates for Sound Transmission Loss Simulations
A Variational Approach to Bayesian Phylogenetic Inference
Efficient Exploration via First-Person Behavior Cloning Assisted Rapidly-Exploring Random Trees
TANDEM: Learning Joint Exploration and Decision Making with Tactile Sensors
Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
Learning Causal Overhypotheses through Exploration in Children and Computational Models
Online Decision Transformer
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search
Lagrangian Manifold Monte Carlo on Monge Patches
Efficient Policy Space Response Oracles
Learning to Act with Affordance-Aware Multimodal Neural SLAM
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
Using Non-Stationary Bandits for Learning in Repeated Cournot Games with Non-Stationary Demand
JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning
A Fast and Scalable Polyatomic Frank-Wolfe Algorithm for the LASSO
HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions
Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning
Discovering and Exploiting Sparse Rewards in a Learned Behavior Space
Bayesian optimization of distributed neurodynamical controller models for spatial navigation
Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning
Map Induction: Compositional spatial submap learning for efficient exploration in novel environments
More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.