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 81–90 of 514 papers

TitleStatusHype
Adaptive teachers for amortized samplersCode0
Provably Efficient Exploration in Inverse Constrained Reinforcement Learning—0
QueryBuilder: Human-in-the-Loop Query Development for Information Retrieval—0
Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal GuidanceCode0
Targeting the partition function of chemically disordered materials with a generative approach based on inverse variational autoencoders—0
Reinforcement Learning for Causal Discovery without Acyclicity Constraints—0
Emotion-Agent: Unsupervised Deep Reinforcement Learning with Distribution-Prototype Reward for Continuous Emotional EEG Analysis—0
Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction—0
Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithm—0
Modeling Multi-Step Scientific Processes with Graph Transformer Networks—0
Show:102550
← PrevPage 9 of 52Next →

No leaderboard results yet.