Risk-Sensitive Stochastic Optimal Control as Rao-Blackwellized Markovian Score Climbing

• URL: http://arxiv.org/abs/2312.14000v1
• Date: Thu, 21 Dec 2023 16:34:03 GMT
• Title: Risk-Sensitive Stochastic Optimal Control as Rao-Blackwellized Markovian Score Climbing
• Authors: Hany Abdulsamad, Sahel Iqbal, Adrien Corenflos, Simo S\"arkk\"a
• Abstract summary: optimal control of dynamical systems is a crucial challenge in sequential decision-making. Control-as-inference approaches have had considerable success, providing a viable risk-sensitive framework to address the exploration-exploitation dilemma. This paper introduces a novel perspective by framing risk-sensitive control as Markovian reinforcement score climbing under samples drawn from a conditional particle filter.
• Score: 3.9410617513331863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making. Recently, control-as-inference approaches have had considerable success, providing a viable risk-sensitive framework to address the exploration-exploitation dilemma. Nonetheless, a majority of these techniques only invoke the inference-control duality to derive a modified risk objective that is then addressed within a reinforcement learning framework. This paper introduces a novel perspective by framing risk-sensitive stochastic control as Markovian score climbing under samples drawn from a conditional particle filter. Our approach, while purely inference-centric, provides asymptotically unbiased estimates for gradient-based policy optimization with optimal importance weighting and no explicit value function learning. To validate our methodology, we apply it to the task of learning neural non-Gaussian feedback policies, showcasing its efficacy on numerical benchmarks of stochastic dynamical systems.

Related papers

• Regularization for Adversarial Robust Learning [18.46110328123008]
  We develop a novel approach to adversarial training that integrates $phi$-divergence regularization into the distributionally robust risk function. This regularization brings a notable improvement in computation compared with the original formulation. We validate our proposed method in supervised learning, reinforcement learning, and contextual learning and showcase its state-of-the-art performance against various adversarial attacks.
  arXiv  Detail & Related papers  (2024-08-19T03:15:41Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Beyond Expectations: Learning with Stochastic Dominance Made Practical [88.06211893690964]
  dominance models risk-averse preferences for decision making with uncertain outcomes. Despite theoretically appealing, the application of dominance in machine learning has been scarce. We first generalize the dominance concept to enable feasible comparisons between any arbitrary pair of random variables. We then develop a simple and efficient approach for finding the optimal solution in terms of dominance.
  arXiv  Detail & Related papers  (2024-02-05T03:21:23Z)
• Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach [3.453622106101339]
  We propose a framework towards achieving two intertwined objectives: (i) equipping reinforcement learning with active exploration and deliberate information gathering, and (ii) overcoming the computational intractability of optimal control law. We approach both objectives by using reinforcement learning to compute the optimal control law. Unlike fixed exploration and exploitation balance, caution and probing are employed automatically by the controller in real-time, even after the learning process is terminated.
  arXiv  Detail & Related papers  (2023-09-18T18:05:35Z)
• Risk-sensitive Actor-free Policy via Convex Optimization [0.0]
  Traditional reinforcement learning methods optimize agents safety, potentially resulting in unintended consequences. We propose an optimal actor-sensitive policy based on a conditional-risk-free network.
  arXiv  Detail & Related papers  (2023-06-30T21:20:04Z)
• Risk-Sensitive Reinforcement Learning with Exponential Criteria [0.0]
  We provide a definition of robust reinforcement learning policies and formulate a risk-sensitive reinforcement learning problem to approximate them. We introduce a novel online Actor-Critic algorithm based on solving a multiplicative Bellman equation using approximation updates. The implementation, performance, and robustness properties of the proposed methods are evaluated in simulated experiments.
  arXiv  Detail & Related papers  (2022-12-18T04:44:38Z)
• Reinforcement Learning Policies in Continuous-Time Linear Systems [0.0]
  We present online policies that learn optimal actions fast by carefully randomizing the parameter estimates. We prove sharp stability results for inexact system dynamics and tightly specify the infinitesimal regret caused by sub-optimal actions. Our analysis sheds light on fundamental challenges in continuous-time reinforcement learning and suggests a useful cornerstone for similar problems.
  arXiv  Detail & Related papers  (2021-09-16T00:08:50Z)
• Probabilistic robust linear quadratic regulators with Gaussian processes [73.0364959221845]
  Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin.
  arXiv  Detail & Related papers  (2021-05-17T08:36:18Z)
• 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)
• Reliable Off-policy Evaluation for Reinforcement Learning [53.486680020852724]
  In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy. We propose a novel framework that provides robust and optimistic cumulative reward estimates using one or multiple logged data.
  arXiv  Detail & Related papers  (2020-11-08T23:16:19Z)
• SAMBA: Safe Model-Based & Active Reinforcement Learning [59.01424351231993]
  SAMBA is a framework for safe reinforcement learning that combines aspects from probabilistic modelling, information theory, and statistics. We evaluate our algorithm on a variety of safe dynamical system benchmarks involving both low and high-dimensional state representations. We provide intuition as to the effectiveness of the framework by a detailed analysis of our active metrics and safety constraints.
  arXiv  Detail & Related papers  (2020-06-12T10:40:46Z)

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.