Goto

Collaborating Authors

 Reinforcement Learning

Exploration by Learning Diverse Skills through Successor State Representations

Neural Information Processing Systems

The ability to perform different skills can encourage agents to explore.

898387e745a0b95e17017d2c795444b6-Paper-Conference.pdf

RL: Efficient Exploration for Nonepisodic RL

Neural Information Processing Systems

RL achieves the optimal average cost while incurring the least regret.

State Chrono Representation for Enhancing Generalization in Reinforcement Learning Jianda Chen 1 Wen Zheng Terence Ng1,2 Zichen Chen

Neural Information Processing Systems

However, these approaches face challenges in demanding generalization tasks and scenarios with non-informative rewards.

Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning

Neural Information Processing Systems

Goal-conditioned reinforcement learning is a powerful way to control an AI agent's

852f50969a9e523ec41d26f2f68bd456-Paper-Conference.pdf

850e8063d902e0825d3c5504d183bafe-Paper-Conference.pdf

83a4ea71b13bc86308a2bd0b5e07fb61-Paper-Conference.pdf

We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both

Neural Information Processing Systems

We argue that these properties are satisfied in many continuous state-action Markov decision processes.

831406cfe7e4a0aed5ac5c8a8389d1f5-Paper-Conference.pdf