An Alternate Policy Gradient Estimator for Softmax Policies

• URL: http://arxiv.org/abs/2112.11622v1
• Date: Wed, 22 Dec 2021 02:01:19 GMT
• Title: An Alternate Policy Gradient Estimator for Softmax Policies
• Authors: Shivam Garg, Samuele Tosatto, Yangchen Pan, Martha White, A. Rupam Mahmood
• Abstract summary: We propose a novel policy gradient estimator for softmax policies. Our analysis and experiments, conducted on bandits and classical MDP benchmarking tasks, show that our estimator is more robust to policy saturation.
• Score: 36.48028448548086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Policy gradient (PG) estimators for softmax policies are ineffective with sub-optimally saturated initialization, which happens when the density concentrates on a sub-optimal action. Sub-optimal policy saturation may arise from bad policy initialization or sudden changes in the environment that occur after the policy has already converged, and softmax PG estimators require a large number of updates to recover an effective policy. This severe issue causes high sample inefficiency and poor adaptability to new situations. To mitigate this problem, we propose a novel policy gradient estimator for softmax policies that utilizes the bias in the critic estimate and the noise present in the reward signal to escape the saturated regions of the policy parameter space. Our analysis and experiments, conducted on bandits and classical MDP benchmarking tasks, show that our estimator is more robust to policy saturation.

Related papers

• CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies [30.57323631122579]
  We focus on threshold policies, a ubiquitous class of policies with applications in economics, healthcare, and digital advertising. Existing methods rely on potentially underpowered safety checks and limit the opportunities for finding safe improvements. We show that in adversarial settings, our approach controls the rate of adopting a policy worse than the baseline to the pre-specified error level.
  arXiv  Detail & Related papers  (2024-08-21T21:38:03Z)
• Importance-Weighted Offline Learning Done Right [16.4989952150404]
  We study the problem of offline policy optimization in contextual bandit problems. The goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. We show that a simple alternative approach based on the "implicit exploration" estimator of citet2015 yields performance guarantees that are superior in nearly all possible terms to all previous results.
  arXiv  Detail & Related papers  (2023-09-27T16:42:10Z)
• Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs [107.28031292946774]
  We study the problem of computing an optimal policy of an infinite-horizon discounted Markov decision process (constrained MDP) We develop two single-time-scale policy-based primal-dual algorithms with non-asymptotic convergence of their policy iterates to an optimal constrained policy. To the best of our knowledge, this work appears to be the first non-asymptotic policy last-iterate convergence result for single-time-scale algorithms in constrained MDPs.
  arXiv  Detail & Related papers  (2023-06-20T17:27:31Z)
• The Role of Baselines in Policy Gradient Optimization [83.42050606055822]
  We show that the emphstate value baseline allows on-policy. emphnatural policy gradient (NPG) to converge to a globally optimal. policy at an $O (1/t) rate gradient. We find that the primary effect of the value baseline is to textbfreduce the aggressiveness of the updates rather than their variance.
  arXiv  Detail & Related papers  (2023-01-16T06:28:00Z)
• Local Policy Improvement for Recommender Systems [8.617221361305901]
  We show how to train a new policy given data collected from a previously-deployed policy. We suggest an alternative approach of local policy improvement without off-policy correction. This local policy improvement paradigm is ideal for recommender systems, as previous policies are typically of decent quality and policies are updated frequently.
  arXiv  Detail & Related papers  (2022-12-22T00:47:40Z)
• Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration [39.250754806600135]
  Policy (PG) estimation becomes a challenge when we are not allowed to sample with the target policy. Conventional methods for off-policy PG estimation often suffer from significant bias or exponentially large variance. In this paper, we propose the double Fitted PG estimation (FPG) algorithm.
  arXiv  Detail & Related papers  (2022-01-31T20:23:52Z)
• 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)
• Policy Optimization as Online Learning with Mediator Feedback [46.845765216238135]
  Policy Optimization (PO) is a widely used approach to address continuous control tasks. In this paper, we introduce the notion of mediator feedback that frames PO as an online learning problem over the policy space. We propose an algorithm, RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RIST) for regret minimization.
  arXiv  Detail & Related papers  (2020-12-15T11:34:29Z)
• Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies [80.42316902296832]
  We study the estimation of policy value and gradient of a deterministic policy from off-policy data when actions are continuous. In this setting, standard importance sampling and doubly robust estimators for policy value and gradient fail because the density ratio does not exist. We propose several new doubly robust estimators based on different kernelization approaches.
  arXiv  Detail & Related papers  (2020-06-06T15:52:05Z)
• Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning [80.42316902296832]
  We study the efficient off-policy evaluation of natural policies, which are defined in terms of deviations from the behavior policy. This is a departure from the literature on off-policy evaluation where most work consider the evaluation of explicitly specified policies.
  arXiv  Detail & Related papers  (2020-06-06T15:08:24Z)
• 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)

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.