Policy Bifurcation in Safe Reinforcement Learning

• URL: http://arxiv.org/abs/2403.12847v3
• Date: Thu, 28 Mar 2024 11:46:02 GMT
• Title: Policy Bifurcation in Safe Reinforcement Learning
• Authors: Wenjun Zou, Yao Lyu, Jie Li, Yujie Yang, Shengbo Eben Li, Jingliang Duan, Xianyuan Zhan, Jingjing Liu, Yaqin Zhang, Keqiang Li,
• Abstract summary: In some scenarios, the feasible policy should be discontinuous or multi-valued, interpolating between discontinuous local optima can inevitably lead to constraint violations. We are the first to identify the generating mechanism of such a phenomenon, and employ topological analysis to rigorously prove the existence of bifurcation in safe RL. We propose a safe RL algorithm called multimodal policy optimization (MUPO), which utilizes a Gaussian mixture distribution as the policy output.
• Score: 35.75059015441807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems. Existing studies in safe RL implicitly assume continuity in policy functions, where policies map states to actions in a smooth, uninterrupted manner; however, our research finds that in some scenarios, the feasible policy should be discontinuous or multi-valued, interpolating between discontinuous local optima can inevitably lead to constraint violations. We are the first to identify the generating mechanism of such a phenomenon, and employ topological analysis to rigorously prove the existence of policy bifurcation in safe RL, which corresponds to the contractibility of the reachable tuple. Our theorem reveals that in scenarios where the obstacle-free state space is non-simply connected, a feasible policy is required to be bifurcated, meaning its output action needs to change abruptly in response to the varying state. To train such a bifurcated policy, we propose a safe RL algorithm called multimodal policy optimization (MUPO), which utilizes a Gaussian mixture distribution as the policy output. The bifurcated behavior can be achieved by selecting the Gaussian component with the highest mixing coefficient. Besides, MUPO also integrates spectral normalization and forward KL divergence to enhance the policy's capability of exploring different modes. Experiments with vehicle control tasks show that our algorithm successfully learns the bifurcated policy and ensures satisfying safety, while a continuous policy suffers from inevitable constraint violations.

Related papers

• Embedding Safety into RL: A New Take on Trust Region Methods [1.5733417396701983]
  Reinforcement Learning (RL) agents are able to solve a wide variety of tasks but are prone to unsafe behaviors. We propose Constrained Trust Region Policy Optimization (C-TRPO), a novel approach that modifies the geometry of the policy space based on the safety constraints.
  arXiv  Detail & Related papers  (2024-11-05T09:55:50Z)
• Flipping-based Policy for Chance-Constrained Markov Decision Processes [9.404184937255694]
  This paper proposes a textitflipping-based policy for Chance-Constrained Markov Decision Processes ( CCMDPs) The flipping-based policy selects the next action by tossing a potentially distorted coin between two action candidates. We demonstrate that the flipping-based policy can improve the performance of the existing safe RL algorithms under the same limits of safety constraints.
  arXiv  Detail & Related papers  (2024-10-09T02:00:39Z)
• Probabilistic Reach-Avoid for Bayesian Neural Networks [71.67052234622781]
  We show that an optimal synthesis algorithm can provide more than a four-fold increase in the number of certifiable states. The algorithm is able to provide more than a three-fold increase in the average guaranteed reach-avoid probability.
  arXiv  Detail & Related papers  (2023-10-03T10:52:21Z)
• Probabilistic Constraint for Safety-Critical Reinforcement Learning [13.502008069967552]
  We consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL) We provide an improved gradient SPG-Actor-Critic that leads to a lower variance than SPG-REINFORCE. We propose a Safe Primal-Dual algorithm that can leverage both SPGs to learn safe policies.
  arXiv  Detail & Related papers  (2023-06-29T19:41:56Z)
• Trust-Region-Free Policy Optimization for Stochastic Policies [60.52463923712565]
  We show that the trust region constraint over policies can be safely substituted by a trust-region-free constraint without compromising the underlying monotonic improvement guarantee. We call the resulting algorithm Trust-REgion-Free Policy Optimization (TREFree) explicit as it is free of any trust region constraints.
  arXiv  Detail & Related papers  (2023-02-15T23:10:06Z)
• Safety-Constrained Policy Transfer with Successor Features [19.754549649781644]
  We propose a Constrained Markov Decision Process (CMDP) formulation that enables the transfer of policies and adherence to safety constraints. Our approach relies on a novel extension of generalized policy improvement to constrained settings via a Lagrangian formulation. Our experiments in simulated domains show that our approach is effective; it visits unsafe states less frequently and outperforms alternative state-of-the-art methods when taking safety constraints into account.
  arXiv  Detail & Related papers  (2022-11-10T06:06:36Z)
• Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence [60.20076757208645]
  This paper proposes a general policy mirror descent (GPMD) algorithm for solving regularized RL. We demonstrate that our algorithm converges linearly over an entire range learning rates, in a dimension-free fashion, to the global solution.
  arXiv  Detail & Related papers  (2021-05-24T02:21:34Z)
• 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)
• Stable Policy Optimization via Off-Policy Divergence Regularization [50.98542111236381]
  Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL) We propose a new algorithm which stabilizes the policy improvement through a proximity term that constrains the discounted state-action visitation distribution induced by consecutive policies to be close to one another. Our proposed method can have a beneficial effect on stability and improve final performance in benchmark high-dimensional control tasks.
  arXiv  Detail & Related papers  (2020-03-09T13:05:47Z)
• BRPO: Batch Residual Policy Optimization [79.53696635382592]
  In batch reinforcement learning, one often constrains a learned policy to be close to the behavior (data-generating) policy. We propose residual policies, where the allowable deviation of the learned policy is state-action-dependent. We derive a new for RL method, BRPO, which learns both the policy and allowable deviation that jointly maximize a lower bound on policy performance.
  arXiv  Detail & Related papers  (2020-02-08T01:59:33Z)

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.