ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
- URL: http://arxiv.org/abs/2302.00808v4
- Date: Fri, 24 May 2024 17:43:35 GMT
- Title: ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
- Authors: Akhil Agnihotri, Rahul Jain, Haipeng Luo,
- Abstract summary: We introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion.
We develop basic sensitivity theory for average CMDPs, and then use the corresponding bounds in the design of the algorithm.
We show its superior empirical performance when compared to other state-of-the-art algorithms adapted for the ACMDPs.
- Score: 36.16736392624796
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Reinforcement Learning (RL) for constrained MDPs (CMDPs) is an increasingly important problem for various applications. Often, the average criterion is more suitable than the discounted criterion. Yet, RL for average-CMDPs (ACMDPs) remains a challenging problem. Algorithms designed for discounted constrained RL problems often do not perform well for the average CMDP setting. In this paper, we introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion. The Average-Constrained Policy Optimization (ACPO) algorithm is inspired by trust region-based policy optimization algorithms. We develop basic sensitivity theory for average CMDPs, and then use the corresponding bounds in the design of the algorithm. We provide theoretical guarantees on its performance, and through extensive experimental work in various challenging OpenAI Gym environments, show its superior empirical performance when compared to other state-of-the-art algorithms adapted for the ACMDPs.
Related papers
- Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.
To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.
Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
arXiv Detail & Related papers (2024-05-26T05:38:50Z) - A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees [28.974797385513263]
We study a primal-dual (PD) reinforcement learning (RL) algorithm for online Markov constrained decision processes (CMDPs)
In this paper, we introduce a novel policy gradient PD algorithm with uniform probably approximate correctness (Uniform-PAC) guarantees, simultaneously ensuring convergence to optimal policies, sublinear regret, and sample complexity for any target accuracy.
Notably, this represents the first Uniform-PAC algorithm for the online CMDP problem.
arXiv Detail & Related papers (2024-01-31T12:23:24Z) - Local Optimization Achieves Global Optimality in Multi-Agent
Reinforcement Learning [139.53668999720605]
We present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO.
We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate.
arXiv Detail & Related papers (2023-05-08T16:20:03Z) - Global Algorithms for Mean-Variance Optimization in Markov Decision
Processes [8.601670707452083]
Dynamic optimization of mean and variance in Markov decision processes (MDPs) is a long-standing challenge caused by the failure of dynamic programming.
We propose a new approach to find the globally optimal policy for combined metrics of steady-state mean and variance in an infinite-horizon undiscounted MDP.
arXiv Detail & Related papers (2023-02-27T12:17:43Z) - Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm.
We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
arXiv Detail & Related papers (2022-09-15T07:22:58Z) - A Policy Efficient Reduction Approach to Convex Constrained Deep
Reinforcement Learning [2.811714058940267]
We propose a new variant of the conditional gradient (CG) type algorithm, which generalizes the minimum norm point (MNP) method.
Our method reduces the memory costs by an order of magnitude, and achieves better performance, demonstrating both its effectiveness and efficiency.
arXiv Detail & Related papers (2021-08-29T20:51:32Z) - Safe Exploration by Solving Early Terminated MDP [77.10563395197045]
We introduce a new approach to address safe RL problems under the framework of Early TerminatedP (ET-MDP)
We first define the ET-MDP as an unconstrained algorithm with the same optimal value function as its corresponding CMDP.
An off-policy algorithm based on context models is then proposed to solve the ET-MDP, which thereby solves the corresponding CMDP with better performance and improved learning efficiency.
arXiv Detail & Related papers (2021-07-09T04:24:40Z) - Variance-Reduced Off-Policy Memory-Efficient Policy Search [61.23789485979057]
Off-policy policy optimization is a challenging problem in reinforcement learning.
Off-policy algorithms are memory-efficient and capable of learning from off-policy samples.
arXiv Detail & Related papers (2020-09-14T16:22:46Z) - Queueing Network Controls via Deep Reinforcement Learning [0.0]
We develop a Proximal policy optimization algorithm for queueing networks.
The algorithm consistently generates control policies that outperform state-of-arts in literature.
A key to the successes of our PPO algorithm is the use of three variance reduction techniques in estimating the relative value function.
arXiv Detail & Related papers (2020-07-31T01:02:57Z) - Fast Global Convergence of Natural Policy Gradient Methods with Entropy
Regularization [44.24881971917951]
Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms.
We develop convergence guarantees for entropy-regularized NPG methods under softmax parameterization.
Our results accommodate a wide range of learning rates, and shed light upon the role of entropy regularization in enabling fast convergence.
arXiv Detail & Related papers (2020-07-13T17:58:41Z) - Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization [71.03797261151605]
Adaptivity is an important yet under-studied property in modern optimization theory.
Our algorithm is proved to achieve the best-available convergence for non-PL objectives simultaneously while outperforming existing algorithms for PL objectives.
arXiv Detail & Related papers (2020-02-13T05:42:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.