Simplification of Risk Averse POMDPs with Performance Guarantees

• URL: http://arxiv.org/abs/2406.03000v2
• Date: Sat, 8 Jun 2024 07:37:12 GMT
• Title: Simplification of Risk Averse POMDPs with Performance Guarantees
• Authors: Yaacov Pariente, Vadim Indelman,
• Abstract summary: Risk averse decision making under uncertainty in partially observable domains is a fundamental problem in AI and essential for reliable autonomous agents. In our case, the problem is modeled using partially observable Markov decision processes (POMDPs), when the value function is the conditional value at risk (CVaR) of the return. Calculating an optimal solution for POMDPs is computationally intractable in general. We develop a simplification framework to speedup the evaluation of the value function, while providing performance guarantees.
• Score: 6.129902017281406
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Risk averse decision making under uncertainty in partially observable domains is a fundamental problem in AI and essential for reliable autonomous agents. In our case, the problem is modeled using partially observable Markov decision processes (POMDPs), when the value function is the conditional value at risk (CVaR) of the return. Calculating an optimal solution for POMDPs is computationally intractable in general. In this work we develop a simplification framework to speedup the evaluation of the value function, while providing performance guarantees. We consider as simplification a computationally cheaper belief-MDP transition model, that can correspond, e.g., to cheaper observation or transition models. Our contributions include general bounds for CVaR that allow bounding the CVaR of a random variable X, using a random variable Y, by assuming bounds between their cumulative distributions. We then derive bounds for the CVaR value function in a POMDP setting, and show how to bound the value function using the computationally cheaper belief-MDP transition model and without accessing the computationally expensive model in real-time. Then, we provide theoretical performance guarantees for the estimated bounds. Our results apply for a general simplification of a belief-MDP transition model and support simplification of both the observation and state transition models simultaneously.

Related papers

• Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes [44.974100402600165]
  We study the evaluation of a policy best-parametric and worst-case perturbations to a decision process (MDP) We use transition observations from the original MDP, whether they are generated under the same or a different policy. Our estimator is also estimated statistical inference using Wald confidence intervals.
  arXiv  Detail & Related papers  (2024-03-29T18:11:49Z)
• Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practice [9.444784653236157]
  We deal with the question of what would be the implication of using simplified observation models for planning. Our main contribution is a novel probabilistic bound based on a statistical total variation distance of the simplified model. Our calculations can be separated into offline and online parts, and we arrive at formal guarantees without having to access the costly model at all during planning.
  arXiv  Detail & Related papers  (2023-11-13T20:55:02Z)
• Non-stationary Reinforcement Learning under General Function Approximation [60.430936031067006]
  We first propose a new complexity metric called dynamic Bellman Eluder (DBE) dimension for non-stationary MDPs. Based on the proposed complexity metric, we propose a novel confidence-set based model-free algorithm called SW-OPEA. We show that SW-OPEA is provably efficient as long as the variation budget is not significantly large.
  arXiv  Detail & Related papers  (2023-06-01T16:19:37Z)
• An Adaptive State Aggregation Algorithm for Markov Decision Processes [10.494611365482028]
  We propose an intuitive algorithm for solving MDPs that reduces the cost of value iteration updates by dynamically grouping together states with similar cost-to-go values. Our algorithm converges almost surely to within (2varepsilon / (1 - gamma) of the true optimal value in the (ellinfty) norm, where (gamma) is the discount factor and aggregated states differ by at most (varepsilon)
  arXiv  Detail & Related papers  (2021-07-23T07:19:43Z)
• Collaborative Nonstationary Multivariate Gaussian Process Model [2.362467745272567]
  We propose a novel model called the collaborative nonstationary Gaussian process model(CNMGP) CNMGP allows us to model data in which outputs do not share a common input set, with a computational complexity independent of the size of the inputs and outputs. We show that our model generally pro-vides better predictive performance than the state-of-the-art, and also provides estimates of time-varying correlations that differ across outputs.
  arXiv  Detail & Related papers  (2021-06-01T18:25:22Z)
• Parallel Stochastic Mirror Descent for MDPs [72.75921150912556]
  We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs) Some variant of Mirror Descent is proposed for convex programming problems with Lipschitz-continuous functionals. We analyze this algorithm in a general case and obtain an estimate of the convergence rate that does not accumulate errors during the operation of the method.
  arXiv  Detail & Related papers  (2021-02-27T19:28:39Z)
• Efficient semidefinite-programming-based inference for binary and multi-class MRFs [83.09715052229782]
  We propose an efficient method for computing the partition function or MAP estimate in a pairwise MRF. We extend semidefinite relaxations from the typical binary MRF to the full multi-class setting, and develop a compact semidefinite relaxation that can again be solved efficiently using the solver.
  arXiv  Detail & Related papers  (2020-12-04T15:36:29Z)
• Exploiting Submodular Value Functions For Scaling Up Active Perception [60.81276437097671]
  In active perception tasks, agent aims to select sensory actions that reduce uncertainty about one or more hidden variables. Partially observable Markov decision processes (POMDPs) provide a natural model for such problems. As the number of sensors available to the agent grows, the computational cost of POMDP planning grows exponentially.
  arXiv  Detail & Related papers  (2020-09-21T09:11:36Z)
• A conditional one-output likelihood formulation for multitask Gaussian processes [0.0]
  Multitask Gaussian processes (MTGP) are the Gaussian process framework's solution for multioutput regression problems. Here we introduce a novel approach that simplifies the multitask learning. We show that it is computationally competitive with state of the art options.
  arXiv  Detail & Related papers  (2020-06-05T14:59:06Z)
• Distributional Robustness and Regularization in Reinforcement Learning [62.23012916708608]
  We introduce a new regularizer for empirical value functions and show that it lower bounds the Wasserstein distributionally robust value function. It suggests using regularization as a practical tool for dealing with $textitexternal uncertainty$ in reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-05T19:56:23Z)
• Plannable Approximations to MDP Homomorphisms: Equivariance under Actions [72.30921397899684]
  We introduce a contrastive loss function that enforces action equivariance on the learned representations. We prove that when our loss is zero, we have a homomorphism of a deterministic Markov Decision Process. We show experimentally that for deterministic MDPs, the optimal policy in the abstract MDP can be successfully lifted to the original MDP.
  arXiv  Detail & Related papers  (2020-02-27T08:29:10Z)

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.