Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
arXiv:2107.01264
Abstract
We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the insight that, in order to achieve a favorable regret, an algorithm does not need to learn how to behave optimally in states that are not reached by an optimal policy. We prove tighter upper regret bounds for optimistic algorithms and accompany them with new information-theoretic lower bounds for a large class of MDPs. Our results show that optimistic algorithms can not achieve the information-theoretic lower bounds even in deterministic MDPs unless there is a unique optimal policy.
References in corpus (14)
- (More) Efficient Reinforcement Learning via Posterior Sampling
- Empirical Bernstein Bounds and Sample Variance Penalization
- Contextual Decision Processes with Low Bellman Rank are PAC-Learnable
- Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
- Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
- On the Sample Complexity of Reinforcement Learning with a Generative Model
- Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
- Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity
- Is Q-learning Provably Efficient?
- Logarithmic Regret for Reinforcement Learning with Linear Function Approximation
- -learning with Logarithmic Regret
- Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
- Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition