Publication

background image
TAAC: Temporally Abstract Actor-Critic for Continuous Control
arXiv Code OpenReview NeurIPS
An Empowerment-based Solution to Robotic Manipulation Tasks with Sparse Rewards
PDF
Generative Particle Variational Inference via Estimation of Functional Gradients
PMLR
Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackers
CVF
Mutual Information State Intrinsic Control
PDF
Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning
PMLR
Hierarchical Reinforcement Learning By Discovering Intrinsic Options
OpenReview PDF Code
Implicit Generative Modeling for Efficient Exploration
PMLR