skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes
We study model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov decision process (MDP), which is more appropriate for applications that involve continuing operations not divided into episodes. In contrast to episodic/discounted MDPs, theoretical understanding of model-free RL algorithms is relatively inadequate for the average-reward setting. In this paper, we consider both the online setting and the setting with access to a simulator. We develop computationally efficient model-free algorithms that achieve sharper guarantees on regret/sample complexity compared with existing results. In the online setting, we design an algorithm, UCB-AVG, based on an optimistic variant of variance-reduced Q-learning. We show that UCB-AVG achieves a regret bound $$\widetilde{O}(S^5A^2sp(h^*)\sqrt{T})$$ after $$T$$ steps, where $$S\times A$$ is the size of state-action space, and $sp(h^*)$ the span of the optimal bias function. Our result provides the first computationally efficient model-free algorithm that achieves the optimal dependence in $$T$$ (up to log factors) for weakly communicating MDPs, which is necessary for low regret. In contrast, prior results either are suboptimal in $$T$$ or require strong assumptions of ergodicity or uniformly mixing of MDPs. In the simulator setting, we adapt the idea of UCB-AVG to develop a model-free algorithm that finds an $$\epsilon$$-optimal policy with sample complexity $$\widetilde{O}(SAsp^2(h^*)\epsilon^{-2} + S^2Asp(h^*)\epsilon^{-1}).$$ This sample complexity is near-optimal for weakly communicating MDPs, in view of the minimax lower bound $$\Omega(SAsp(^*)\epsilon^{-2})$$. Existing work mainly focuses on ergodic MDPs and the results typically depend on $$t_{mix},$$ the worst-case mixing time induced by a policy. We remark that the diameter $$D$$ and mixing time $$t_{mix}$$ are both lower bounded by $sp(h^*)$, and $$t_{mix}$$ can be arbitrarily large for certain MDPs. On the technical side, our approach integrates two key ideas: learning an $$\gamma$$-discounted MDP as an approximation, and leveraging reference-advantage decomposition for variance in optimistic Q-learning. As recognized in prior work, a naive approximation by discounted MDPs results in suboptimal guarantees. A distinguishing feature of our method is maintaining estimates of value-difference between state pairs to provide a sharper bound on the variance of reference advantage. We also crucially use a careful choice of the discounted factor $$\gamma$$ to balance approximation error due to discounting and the statistical learning error, and we are able to maintain a good-quality reference value function with $O(SA)$ space complexity.  more » « less
Award ID(s):
1955997
PAR ID:
10435562
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Conference on Learning Theory
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR)
    Dasgupta, Sanjoy; Mandt, Stephan; Li, Yingzhen (Ed.)
    Average reward reinforcement learning (RL) provides a suitable framework for capturing the objective (i.e. long-run average reward) for continuing tasks, where there is often no natural way to identify a discount factor. However, existing average reward RL algorithms with sample complexity guarantees are not feasible, as they take as input the (unknown) mixing time of the Markov decision process (MDP). In this paper, we make initial progress towards addressing this open problem. We design a feasible average-reward $$Q$$-learning framework that requires no knowledge of any problem parameter as input. Our framework is based on discounted $$Q$$-learning, while we dynamically adapt the discount factor (and hence the effective horizon) to progressively approximate the average reward. In the synchronous setting, we solve three tasks: (i) learn a policy that is $$\epsilon$$-close to optimal, (ii) estimate optimal average reward with $$\epsilon$$-accuracy, and (iii) estimate the bias function (similar to $$Q$$-function in discounted case) with $$\epsilon$$-accuracy. We show that with carefully designed adaptation schemes, (i) can be achieved with $$\tilde{O}(\frac{SA t_{\mathrm{mix}}^{8}}{\epsilon^{8}})$$ samples, (ii) with $$\tilde{O}(\frac{SA t_{\mathrm{mix}}^5}{\epsilon^5})$$ samples, and (iii) with $$\tilde{O}(\frac{SA B}{\epsilon^9})$$ samples, where $$t_\mathrm{mix}$$ is the mixing time, and $B > 0$ is an MDP-dependent constant. To our knowledge, we provide the first finite-sample guarantees that are polynomial in $$S, A, t_{\mathrm{mix}}, \epsilon$$ for a feasible variant of $$Q$$-learning. That said, the sample complexity bounds have tremendous room for improvement, which we leave for the community’s best minds. Preliminary simulations verify that our framework is effective without prior knowledge of parameters as input. 
    more » « less
  2. ; ; ; (, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR)
    Dasgupta, Sanjoy; Mandt, Stephan; Li, Yingzhen (Ed.)
    Average reward reinforcement learning (RL) provides a suitable framework for capturing the objective (i.e. long-run average reward) for continuing tasks, where there is often no natural way to identify a discount factor. However, existing average reward RL algorithms with sample complexity guarantees are not feasible, as they take as input the (unknown) mixing time of the Markov decision process (MDP). In this paper, we make initial progress towards addressing this open problem. We design a feasible average-reward $$Q$$-learning framework that requires no knowledge of any problem parameter as input. Our framework is based on discounted $$Q$$-learning, while we dynamically adapt the discount factor (and hence the effective horizon) to progressively approximate the average reward. In the synchronous setting, we solve three tasks: (i) learn a policy that is $$\epsilon$$-close to optimal, (ii) estimate optimal average reward with $$\epsilon$$-accuracy, and (iii) estimate the bias function (similar to $$Q$$-function in discounted case) with $$\epsilon$$-accuracy. We show that with carefully designed adaptation schemes, (i) can be achieved with $$\tilde{O}(\frac{SA t_{\mathrm{mix}}^{8}}{\epsilon^{8}})$$ samples, (ii) with $$\tilde{O}(\frac{SA t_{\mathrm{mix}}^5}{\epsilon^5})$$ samples, and (iii) with $$\tilde{O}(\frac{SA B}{\epsilon^9})$$ samples, where $$t_\mathrm{mix}$$ is the mixing time, and $B > 0$ is an MDP-dependent constant. To our knowledge, we provide the first finite-sample guarantees that are polynomial in $$S, A, t_{\mathrm{mix}}, \epsilon$$ for a feasible variant of $$Q$$-learning. That said, the sample complexity bounds have tremendous room for improvement, which we leave for the community’s best minds. Preliminary simulations verify that our framework is effective without prior knowledge of parameters as input. 
    more » « less
  3. ; ; ; (, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR)
    Dasgupta, Sanjoy; Mandt, Stephan; Li, Yingzhen (Ed.)
    Average reward reinforcement learning (RL) provides a suitable framework for capturing the objective (i.e. long-run average reward) for continuing tasks, where there is often no natural way to identify a discount factor. However, existing average reward RL algorithms with sample complexity guarantees are not feasible, as they take as input the (unknown) mixing time of the Markov decision process (MDP). In this paper, we make initial progress towards addressing this open problem. We design a feasible average-reward $$Q$$-learning framework that requires no knowledge of any problem parameter as input. Our framework is based on discounted $$Q$$-learning, while we dynamically adapt the discount factor (and hence the effective horizon) to progressively approximate the average reward. In the synchronous setting, we solve three tasks: (i) learn a policy that is $$\epsilon$$-close to optimal, (ii) estimate optimal average reward with $$\epsilon$$-accuracy, and (iii) estimate the bias function (similar to $$Q$$-function in discounted case) with $$\epsilon$$-accuracy. We show that with carefully designed adaptation schemes, (i) can be achieved with $$\tilde{O}(\frac{SA t_{\mathrm{mix}}^{8}}{\epsilon^{8}})$$ samples, (ii) with $$\tilde{O}(\frac{SA t_{\mathrm{mix}}^5}{\epsilon^5})$$ samples, and (iii) with $$\tilde{O}(\frac{SA B}{\epsilon^9})$$ samples, where $$t_\mathrm{mix}$$ is the mixing time, and $B > 0$ is an MDP-dependent constant. To our knowledge, we provide the first finite-sample guarantees that are polynomial in $$S, A, t_{\mathrm{mix}}, \epsilon$$ for a feasible variant of $$Q$$-learning. That said, the sample complexity bounds have tremendous room for improvement, which we leave for the community’s best minds. Preliminary simulations verify that our framework is effective without prior knowledge of parameters as input. 
    more » « less
  4. (, Proceedings of Machine Learning Research)
    Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-reward Markov Decision Processes (MDPs). The first algorithm reduces the problem to the discounted-reward version and achieves O(𝑇^2/3) regret after 𝑇 steps, under the minimal assumption of weakly communicating MDPs. To our knowledge, this is the first model-free algorithm for general MDPs in this setting. The second algorithm makes use of recent advances in adaptive algorithms for adversarial multi-armed bandits and improves the regret to O(T^{1/2}), albeit with a stronger ergodic assumption. This result significantly improves over the O(T^{3/4}) regret achieved by the only existing model-free algorithm by Abbasi-Yadkori et al. (2019) for ergodic MDPs in the infinite-horizon average-reward setting. 
    more » « less
  5. ; ; ; ; (, Proceedings of Machine Learning Research)
    Recent studies in reinforcement learning (RL) have made significant progress by leveraging function approximation to alleviate the sample complexity hurdle for better performance. Despite the success, existing provably efficient algorithms typically rely on the accessibility of immediate feedback upon taking actions. The failure to account for the impact of delay in observations can significantly degrade the performance of real-world systems due to the regret blow-up. In this work, we tackle the challenge of delayed feedback in RL with linear function approximation by employing posterior sampling, which has been shown to empirically outperform the popular UCB algorithms in a wide range of regimes. We first introduce Delayed-PSVI, an optimistic value-based algorithm that effectively explores the value function space via noise perturbation with posterior sampling. We provide the first analysis for posterior sampling algorithms with delayed feedback in RL and show our algorithm achieves $$\widetilde{O}(\sqrt{d^3H^3 T} + d^2H^2 E[\tau])$$ worst-case regret in the presence of unknown stochastic delays. Here $$E[\tau]$$ is the expected delay. To further improve its computational efficiency and to expand its applicability in high-dimensional RL problems, we incorporate a gradient-based approximate sampling scheme via Langevin dynamics for Delayed-LPSVI, which maintains the same order-optimal regret guarantee with $$\widetilde{O}(dHK)$$ computational cost. Empirical evaluations are performed to demonstrate the statistical and computational efficacy of our algorithms. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email