Reinforcement Learning in POMDPs Without Resets

By Eyal Even-Dar, Sham M. Kakade, Yishay Mansour. 2005

53 citations recorded by the source corpus.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Igor Mordatch
2. Sergey Levine
3. Pieter Abbeel
4. Kevin Lu
5. Aditya Grover
6. Marcus Hutter
7. Tor Lattimore
8. Chelsea Finn

Citations in the corpus

• Reset-Free Lifelong Learning with Skill-Space Planning (2020, background): “The traditional approach to non-episodic RL is to explicitly learn a policy to reset the environment (Even-Dar et al., 2005; Han et al., 2015; Eysenbach et al., 2017).”
• The Sample-Complexity of General Reinforcement Learning (2013, background): “Policy π is (cid:15) -optimal in history h and environment The sample-complexity of a policy π in environment class M is the smallest Λ such that, with high probability, π is (cid:15) -optimal for all but Λ time-steps for all µ ∈ M .”