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.
Bag of Policies for Distributional Deep Exploration
Towards A Unified Agent with Foundation Models
LISSNAS: Locality-based Iterative Search Space Shrinkage for Neural Architecture Search
Approximate information for efficient exploration-exploitation strategies
Improving Protein Optimization with Smoothed Fitness Landscapes
Maximum State Entropy Exploration using Predecessor and Successor Representations
DISCO-10M: A Large-Scale Music Dataset
Inferring Hierarchical Structure in Multi-Room Maze Environments
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm
Magnitude Attention-based Dynamic Pruning
Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search
Large-Batch, Iteration-Efficient Neural Bayesian Design Optimization
A Survey of Label-Efficient Deep Learning for 3D Point Clouds
EXPODE: EXploiting POlicy Discrepancy for Efficient Exploration in Multi-agent Reinforcement Learning
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
Successor-Predecessor Intrinsic Exploration
Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models
Joint Falsification and Fidelity Settings Optimization for Validation of Safety-Critical Systems: A Theoretical Analysis
Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization
Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning
Fast exploration and learning of latent graphs with aliased observations
Exploration of the search space of Gaussian graphical models for paired data
Policy Mirror Descent Inherently Explores Action Space
Exploration via Epistemic Value Estimation
Guarded Policy Optimization with Imperfect Online Demonstrations
Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization
Efficient Informed Proposals for Discrete Distributions via Newton's Series Approximation
Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot
Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.