Performative Reinforcement Learning in Gradually Shifting Environments

• URL: http://arxiv.org/abs/2402.09838v2
• Date: Fri, 31 May 2024 13:59:44 GMT
• Title: Performative Reinforcement Learning in Gradually Shifting Environments
• Authors: Ben Rank, Stelios Triantafyllou, Debmalya Mandal, Goran Radanovic,
• Abstract summary: When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy as well as its previous dynamics.
• Score: 13.524274041966539
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy as well as its previous dynamics. This is a generalization of Performative RL (PRL) [Mandal et al., 2023]. Unlike PRL, our framework allows to model scenarios where the environment gradually adjusts to a deployed policy. We adapt two algorithms from the performative prediction literature to our setting and propose a novel algorithm called Mixed Delayed Repeated Retraining (MDRR). We provide conditions under which these algorithms converge and compare them using three metrics: number of retrainings, approximation guarantee, and number of samples per deployment. MDRR is the first algorithm in this setting which combines samples from multiple deployments in its training. This makes MDRR particularly suitable for scenarios where the environment's response strongly depends on its previous dynamics, which are common in practice. We experimentally compare the algorithms using a simulation-based testbed and our results show that MDRR converges significantly faster than previous approaches.

Related papers

• 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)
• Causal Coordinated Concurrent Reinforcement Learning [8.654978787096807]
  We propose a novel algorithmic framework for data sharing and coordinated exploration for the purpose of learning more data-efficient and better performing policies under a concurrent reinforcement learning setting. Our algorithm leverages a causal inference algorithm in the form of Additive Noise Model - Mixture Model (ANM-MM) in extracting model parameters governing individual differentials via independence enforcement. We propose a new data sharing scheme based on a similarity measure of the extracted model parameters and demonstrate superior learning speeds on a set of autoregressive, pendulum and cart-pole swing-up tasks.
  arXiv  Detail & Related papers  (2024-01-31T17:20:28Z)
• $K$-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control [0.6906005491572401]
  We propose a novel $K$-nearest neighbor reparametric procedure for estimating the performance of a policy from historical data. Our analysis allows for the sampling of entire episodes, as is common practice in most applications. Compared to other OPE methods, our algorithm does not require optimization, can be efficiently implemented via tree-based nearest neighbor search and parallelization, and does not explicitly assume a parametric model for the environment's dynamics.
  arXiv  Detail & Related papers  (2023-06-07T23:55:12Z)
• State Regularized Policy Optimization on Data with Dynamics Shift [25.412472472457324]
  In many real-world scenarios, Reinforcement Learning (RL) algorithms are trained on data with dynamics shift, i.e., with different underlying environment dynamics. In this paper, we find that in many environments with similar structures and different dynamics, optimal policies have similar stationary state distributions. Such distribution is used to regularize the policy trained in a new environment, leading to the SRPO (textbfS textbfRegularized textbfPolicy textbfOptimization) algorithm.
  arXiv  Detail & Related papers  (2023-06-06T10:06:09Z)
• One-Step Distributional Reinforcement Learning [10.64435582017292]
  We present the simpler one-step distributional reinforcement learning (OS-DistrRL) framework. We show that our approach comes with a unified theory for both policy evaluation and control. We propose two OS-DistrRL algorithms for which we provide an almost sure convergence analysis.
  arXiv  Detail & Related papers  (2023-04-27T06:57:00Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration [7.930709072852582]
  We propose a generic framework for Learning from Demonstration (LfD) based on actor-critic algorithms. We conduct experiments on 4 standard benchmark environments in Mujoco and 2 self-designed robotic environments.
  arXiv  Detail & Related papers  (2021-09-27T12:42:05Z)
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective [52.497514255040514]
  This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes. Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2021-05-03T07:23:39Z)
• Phase Retrieval using Expectation Consistent Signal Recovery Algorithm based on Hypernetwork [73.94896986868146]
  Phase retrieval is an important component in modern computational imaging systems. Recent advances in deep learning have opened up a new possibility for robust and fast PR. We develop a novel framework for deep unfolding to overcome the existing limitations.
  arXiv  Detail & Related papers  (2021-01-12T08:36:23Z)
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment [55.91291559442884]
  This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment. We propose to build the notion of continual learning into the modeling process of learning wireless systems. Our design is based on a novel min-max formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2020-11-16T08:24:34Z)
• Robust Reinforcement Learning via Adversarial training with Langevin Dynamics [51.234482917047835]
  We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. We present a novel, scalable two-player RL algorithm, which is a sampling variant of the two-player policy method.
  arXiv  Detail & Related papers  (2020-02-14T14:59:14Z)

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.