SOTAVerified

Efficient Exploration

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 226–250 of 514 papers

TitleStatusHype
Towards A Unified Agent with Foundation Models—0
LISSNAS: Locality-based Iterative Search Space Shrinkage for Neural Architecture Search—0
Approximate information for efficient exploration-exploitation strategies—0
Maximum State Entropy Exploration using Predecessor and Successor Representations—0
DISCO-10M: A Large-Scale Music Dataset—0
Inferring Hierarchical Structure in Multi-Room Maze Environments—0
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP—0
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning—0
PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm—0
Magnitude Attention-based Dynamic Pruning—0
Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial OptimizationCode0
Large-Batch, Iteration-Efficient Neural Bayesian Design OptimizationCode0
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search—0
EXPODE: EXploiting POlicy Discrepancy for Efficient Exploration in Multi-agent Reinforcement LearningCode0
Successor-Predecessor Intrinsic Exploration—0
Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution—0
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models—0
Joint Falsification and Fidelity Settings Optimization for Validation of Safety-Critical Systems: A Theoretical Analysis—0
Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization—0
Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement LearningCode0
Fast exploration and learning of latent graphs with aliased observations—0
Exploration of the search space of Gaussian graphical models for paired data—0
Policy Mirror Descent Inherently Explores Action Space—0
Exploration via Epistemic Value Estimation—0
Guarded Policy Optimization with Imperfect Online Demonstrations—0
Show:102550
← PrevPage 10 of 21Next →

No leaderboard results yet.