Multi-Objective Policy Gradients with Topological Constraints

• URL: http://arxiv.org/abs/2209.07096v1
• Date: Thu, 15 Sep 2022 07:22:58 GMT
• Title: Multi-Objective Policy Gradients with Topological Constraints
• Authors: Kyle Hollins Wray, Stas Tiomkin, Mykel J. Kochenderfer, Pieter Abbeel
• Abstract summary: 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.
• Score: 108.10241442630289
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently developed theory of topological Markov decision processes (TMDPs) captures this range of problems for the case of discrete states and actions. In this work, we extend TMDPs towards continuous spaces and unknown transition dynamics by formulating, proving, and implementing the policy gradient theorem for TMDPs. This theoretical result enables the creation of TMDP learning algorithms that use function approximators, and can generalize existing deep reinforcement learning (DRL) approaches. Specifically, 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.

Related papers

• Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form [26.01796404477275]
  This paper presents the first algorithm capable of identifying a near-optimal policy in a robust constrained MDP (RCMDP) An optimal policy minimizes cumulative cost while satisfying constraints in the worst-case scenario across a set of environments.
  arXiv  Detail & Related papers  (2024-08-29T06:37:16Z)
• Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning [62.81324245896717]
  We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-ite convergence guarantees under (weak) gradient domination assumptions. We numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-07-15T14:54:57Z)
• MDP Geometry, Normalization and Value Free Solvers [15.627546283580166]
  The Markov Decision Process (MDP) is a widely used mathematical model for sequential decision-making problems. We show that MDPs can be divided into equivalence classes with indistinguishable key solving algorithms dynamics.
  arXiv  Detail & Related papers  (2024-07-09T09:39:45Z)
• Constrained Reinforcement Learning with Average Reward Objective: Model-Based and Model-Free Algorithms [34.593772931446125]
  monograph focuses on the exploration of various model-based and model-free approaches for Constrained within the context of average reward Markov Decision Processes (MDPs) The primal-dual policy gradient-based algorithm is explored as a solution for constrained MDPs.
  arXiv  Detail & Related papers  (2024-06-17T12:46:02Z)
• Two-Stage ML-Guided Decision Rules for Sequential Decision Making under Uncertainty [55.06411438416805]
  Sequential Decision Making under Uncertainty (SDMU) is ubiquitous in many domains such as energy, finance, and supply chains. Some SDMU are naturally modeled as Multistage Problems (MSPs) but the resulting optimizations are notoriously challenging from a computational standpoint. This paper introduces a novel approach Two-Stage General Decision Rules (TS-GDR) to generalize the policy space beyond linear functions. The effectiveness of TS-GDR is demonstrated through an instantiation using Deep Recurrent Neural Networks named Two-Stage Deep Decision Rules (TS-LDR)
  arXiv  Detail & Related papers  (2024-05-23T18:19:47Z)
• Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods [0.40964539027092917]
  Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In practice all parameters are often trained simultaneously, ignoring the inherent structure suggested by dynamic programming. This paper introduces a combination of dynamic programming and policy gradient called dynamic policy gradient, where the parameters are trained backwards in time.
  arXiv  Detail & Related papers  (2023-10-04T09:21:01Z)
• A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments [15.794728813746397]
  Multi-objective reinforcement learning methods fuse the reinforcement learning paradigm with multi-objective optimization techniques. One major drawback of these methods is the lack of adaptability to non-stationary dynamics in the environment. We propose a novel multi-objective reinforcement learning algorithm that can robustly evolve a convex coverage set of policies in an online manner in non-stationary environments.
  arXiv  Detail & Related papers  (2023-08-18T02:15:12Z)
• Provably Efficient UCB-type Algorithms For Learning Predictive State Representations [55.00359893021461]
  The sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs) This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
  arXiv  Detail & Related papers  (2023-07-01T18:35:21Z)
• Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic [59.94347858883343]
  This paper investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) The novelty is to design an embedded product MDP (EP-MDP) between the LDGBA and the MDP. The proposed LDGBA-based reward shaping and discounting schemes for the model-free reinforcement learning (RL) only depend on the EP-MDP states.
  arXiv  Detail & Related papers  (2021-02-24T01:11:25Z)
• Deep Policy Dynamic Programming for Vehicle Routing Problems [89.96386273895985]
  We propose Deep Policy Dynamic Programming (D PDP) to combine the strengths of learned neurals with those of dynamic programming algorithms. D PDP prioritizes and restricts the DP state space using a policy derived from a deep neural network, which is trained to predict edges from example solutions. We evaluate our framework on the travelling salesman problem (TSP) and the vehicle routing problem (VRP) and show that the neural policy improves the performance of (restricted) DP algorithms.
  arXiv  Detail & Related papers  (2021-02-23T15:33:57Z)

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.