Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning

By Kavitha Lakshmanan, Ronald Ortner, Daniil Ryabko. 2015

41 citations recorded by the source corpus.

How researchers see this paper

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

1. Sergey Levine
2. Simon Shaolei Du
3. Alekh Agarwal
4. Nan Jiang
5. Tengyu Ma
6. Yuanzhi Li
7. Wen Sun
8. Yoshua Bengio

Citations in the corpus

• Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees (2018, background): “(See (Jaksch et al., 2010; Bartlett & Tewari, 2009; Fruit et al., 2018; Lakshmanan et al., 2015; Pirotta et al., 2015; 2013) and references therein for the OFU principle in finite-state MDPs.) The main novelty here is to optimize the lower bound directly, without explicitly building any confidence…”
• Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches (2018, background): “With rich observations, many prior works either focus on structured control settings like LQRs (Abbasi-Yadkori and Szepesvári, 2011; Dean et al., 2018) or Lipschitz-continuous MDPs (Kakade et al., 2003; Ortner and Ryabko, 2012; Pazis and Parr, 2013; Lakshmanan et al., 2015).”
• Regret Bounds for Kernel-Based Reinforcement Learning (2020, methodology): “This work was later extended by Lakshmanan et al. (2015) to use a kernel density estimator instead of a frequency estimator for each region of the fixed discretization.”
• Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning (2018, methodology): “Indeed, existing algorithms achieving regret guarantees in this framework (Ortner and Ryabko, 2012; Lakshmanan et al., 2015) all rely on REGAL.”