Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes

• URL: http://arxiv.org/abs/2002.12086v1
• Date: Thu, 27 Feb 2020 13:36:36 GMT
• Title: Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes
• Authors: Tomas Brazdil, Krishnendu Chatterjee, Petr Novotny, Jiri Vahala
• Abstract summary: Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. We consider MDPswith discounted-sum payoff with failure states which repre-sent catastrophic outcomes. Our maincontribution is an efficient risk-constrained planning algo-rithm that combines UCT-like search with a predictor learnedthrough interaction with the MDP.
• Score: 5.081241420920605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which ignores low probability catastrophic events withhighly negative impact on the system. On the other hand,risk-averse policies require the probability of undesirableevents to be below a given threshold, but they do not accountfor optimization of the expected payoff. We consider MDPswith discounted-sum payoff with failure states which repre-sent catastrophic outcomes. The objective of risk-constrainedplanning is to maximize the expected discounted-sum payoffamong risk-averse policies that ensure the probability to en-counter a failure state is below a desired threshold. Our maincontribution is an efficient risk-constrained planning algo-rithm that combines UCT-like search with a predictor learnedthrough interaction with the MDP (in the style of AlphaZero)and with a risk-constrained action selection via linear pro-gramming. We demonstrate the effectiveness of our approachwith experiments on classical MDPs from the literature, in-cluding benchmarks with an order of 10^6 states.

Related papers

• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Risk-Averse MDPs under Reward Ambiguity [9.929659318167731]
  We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. A scalable first-order algorithm is designed to solve large-scale problems.
  arXiv  Detail & Related papers  (2023-01-03T11:06:30Z)
• Conformal Off-Policy Prediction in Contextual Bandits [54.67508891852636]
  Conformal off-policy prediction can output reliable predictive intervals for the outcome under a new target policy. We provide theoretical finite-sample guarantees without making any additional assumptions beyond the standard contextual bandit setup.
  arXiv  Detail & Related papers  (2022-06-09T10:39:33Z)
• Under-Approximating Expected Total Rewards in POMDPs [68.8204255655161]
  We consider the optimal expected total reward to reach a goal state in a partially observable Markov decision process (POMDP) We use mixed-integer linear programming (MILP) to find such minimal probability shifts and experimentally show that our techniques scale quite well.
  arXiv  Detail & Related papers  (2022-01-21T16:43:03Z)
• Risk-Averse Decision Making Under Uncertainty [18.467950783426947]
  A large class of decision making under uncertainty problems can be described via Markov decision processes (MDPs) or partially observable MDPs (POMDPs) In this paper, we consider the problem of designing policies for MDPs and POMDPs with objectives and constraints in terms of dynamic coherent risk measures.
  arXiv  Detail & Related papers  (2021-09-09T07:52:35Z)
• Risk-Averse Stochastic Shortest Path Planning [25.987787625028204]
  We show that optimal, stationary, Markovian policies exist and can be found via a special Bellman's equation. A rover navigation MDP is used to illustrate the proposed methodology with conditional-value-at-risk (CVaR) and entropic-value-at-risk (EVaR) coherent risk measures.
  arXiv  Detail & Related papers  (2021-03-26T20:49:14Z)
• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy [95.98698822755227]
  We make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. We propose an actor-critic algorithm that iteratively and efficiently updates the policy, the Lagrange multiplier, and the Fenchel dual variable.
  arXiv  Detail & Related papers  (2020-12-28T05:02:26Z)
• Selective Classification via One-Sided Prediction [54.05407231648068]
  One-sided prediction (OSP) based relaxation yields an SC scheme that attains near-optimal coverage in the practically relevant high target accuracy regime. We theoretically derive bounds generalization for SC and OSP, and empirically we show that our scheme strongly outperforms state of the art methods in coverage at small error levels.
  arXiv  Detail & Related papers  (2020-10-15T16:14:27Z)
• Cautious Reinforcement Learning via Distributional Risk in the Dual Domain [45.17200683056563]
  We study the estimation of risk-sensitive policies in reinforcement learning problems defined by a Markov Decision Process (MDPs) whose state and action spaces are countably finite. We propose a new definition of risk, which we call caution, as a penalty function added to the dual objective of the linear programming (LP) formulation of reinforcement learning.
  arXiv  Detail & Related papers  (2020-02-27T23:18:04Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)

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.