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 371–380 of 514 papers

TitleStatusHype
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
Scaling MAP-Elites to Deep NeuroevolutionCode1
Optimistic Exploration even with a Pessimistic InitialisationCode1
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
Show:102550
← PrevPage 38 of 52Next →

No leaderboard results yet.