This is the authors' abstract. We don't add key points for this paper.
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimization and function approximation. The first part admits a standard online-learning analysis, and the second part can be quantified independently of the learning algorithm. Therefore, the proposed reduction can be used as a tool to systematically design new RL algorithms. We demonstrate this idea by devising a simple RL algorithm based on mirror descent and the generative-model oracle. For any $γ$-discounted tabular RL problem, with probability at least $1-δ$, it learns an $ε$-optimal policy using at most Õ(|S||A|log(1δ)(1-γ)⁴ε²) samples. Furthermore, this algorithm admits a direct extension to linearly parameterized function approximators for large-scale applications, with computation and sample complexities independent of |S|,|A|, though at the cost of potential approximation bias.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Cheng et al. (2019) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: