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 376–400 of 514 papers

TitleStatusHype
Bayesian optimisation of large-scale photonic reservoir computers—0
Weakly-Supervised Reinforcement Learning for Controllable Behavior—0
Provably Efficient Exploration for Reinforcement Learning Using Unsupervised LearningCode0
Active Model Estimation in Markov Decision Processes—0
Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path—0
Efficient exploration of zero-sum stochastic games—0
Particle Filter Based Monocular Human Tracking with a 3D Cardbox Model and a Novel Deterministic Resampling Strategy—0
Misspecification-robust likelihood-free inference in high dimensions—0
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization—0
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal BabblingCode0
Parameterized Indexed Value Function for Efficient Exploration in Reinforcement LearningCode0
Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning—0
Provably Efficient Exploration in Policy Optimization—0
Explicit Planning for Efficient Exploration in Reinforcement Learning—0
Better Exploration with Optimistic Actor CriticCode0
Comprehensive decision-strategy space exploration for efficient territorial planning strategies—0
Scaling active inference—0
Bayesian Curiosity for Efficient Exploration in Reinforcement LearningCode0
Implicit Generative Modeling for Efficient Exploration—0
Efficient Exploration through Intrinsic Motivation Learning for Unsupervised Subgoal Discovery in Model-Free Hierarchical Reinforcement Learning—0
Multi-Path Policy Optimization—0
MAME : Model-Agnostic Meta-Exploration—0
Neural Contextual Bandits with UCB-based ExplorationCode0
Structured exploration in the finite horizon linear quadratic dual control problem—0
VASE: Variational Assorted Surprise Exploration for Reinforcement Learning—0
Show:102550
← PrevPage 16 of 21Next →

No leaderboard results yet.