Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms

• URL: http://arxiv.org/abs/2312.07178v2
• Date: Mon, 22 Jan 2024 10:31:56 GMT
• Title: Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms
• Authors: Manon Flageat, Bryan Lim, Antoine Cully
• Abstract summary: Many applications in Reinforcement Learning (RL) have noise ority present in the environment. These uncertainties lead the exact same policy to perform differently, from one roll-out to another. Common evaluation procedures in RL summarise the consequent return distributions using solely the expected return, which does not account for the spread of the distribution. Our work defines this spread as the policy: the ability of a policy to obtain similar performance when rolled out many times, a crucial property in some real-world applications.
• Score: 9.649114720478872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many applications in Reinforcement Learning (RL) usually have noise or stochasticity present in the environment. Beyond their impact on learning, these uncertainties lead the exact same policy to perform differently, i.e. yield different return, from one roll-out to another. Common evaluation procedures in RL summarise the consequent return distributions using solely the expected return, which does not account for the spread of the distribution. Our work defines this spread as the policy reproducibility: the ability of a policy to obtain similar performance when rolled out many times, a crucial property in some real-world applications. We highlight that existing procedures that only use the expected return are limited on two fronts: first an infinite number of return distributions with a wide range of performance-reproducibility trade-offs can have the same expected return, limiting its effectiveness when used for comparing policies; second, the expected return metric does not leave any room for practitioners to choose the best trade-off value for considered applications. In this work, we address these limitations by recommending the use of Lower Confidence Bound, a metric taken from Bayesian optimisation that provides the user with a preference parameter to choose a desired performance-reproducibility trade-off. We also formalise and quantify policy reproducibility, and demonstrate the benefit of our metrics using extensive experiments of popular RL algorithms on common uncertain RL tasks.

Related papers

• Policy Gradient with Active Importance Sampling [55.112959067035916]
  Policy gradient (PG) methods significantly benefit from IS, enabling the effective reuse of previously collected samples. However, IS is employed in RL as a passive tool for re-weighting historical samples. We look for the best behavioral policy from which to collect samples to reduce the policy gradient variance.
  arXiv  Detail & Related papers  (2024-05-09T09:08:09Z)
• Distributional Reinforcement Learning with Dual Expectile-Quantile Regression [51.87411935256015]
  quantile regression approach to distributional RL provides flexible and effective way of learning arbitrary return distributions. We show that distributional guarantees vanish, and we empirically observe that the estimated distribution rapidly collapses to its mean estimation. Motivated by the efficiency of $L$-based learning, we propose to jointly learn expectiles and quantiles of the return distribution in a way that allows efficient learning while keeping an estimate of the full distribution of returns.
  arXiv  Detail & Related papers  (2023-05-26T12:30:05Z)
• Quantile Off-Policy Evaluation via Deep Conditional Generative Learning [21.448553360543478]
  Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy. We propose a doubly-robust inference procedure for quantile OPE in sequential decision making. We demonstrate the advantages of this proposed estimator through both simulations and a real-world dataset from a short-video platform.
  arXiv  Detail & Related papers  (2022-12-29T22:01:43Z)
• BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning [14.432131909590824]
  Offline Reinforcement Learning aims to train effective policies using previously collected datasets. Standard off-policy RL algorithms are prone to overestimations of the values of out-of-distribution (less explored) actions. We improve the behavior regularized offline reinforcement learning and propose BRAC+.
  arXiv  Detail & Related papers  (2021-10-02T23:55:49Z)
• Universal Off-Policy Evaluation [64.02853483874334]
  We take the first steps towards a universal off-policy estimator (UnO) We use UnO for estimating and simultaneously bounding the mean, variance, quantiles/median, inter-quantile range, CVaR, and the entire cumulative distribution of returns.
  arXiv  Detail & Related papers  (2021-04-26T18:54:31Z)
• Bayesian Distributional Policy Gradients [2.28438857884398]
  Distributional Reinforcement Learning maintains the entire probability distribution of the reward-to-go, i.e. the return. Bayesian Distributional Policy Gradients (BDPG) uses adversarial training in joint-contrastive learning to estimate a variational posterior from the returns.
  arXiv  Detail & Related papers  (2021-03-20T23:42:50Z)
• Variance Penalized On-Policy and Off-Policy Actor-Critic [60.06593931848165]
  We propose on-policy and off-policy actor-critic algorithms that optimize a performance criterion involving both mean and variance in the return. Our approach not only performs on par with actor-critic and prior variance-penalization baselines in terms of expected return, but also generates trajectories which have lower variance in the return.
  arXiv  Detail & Related papers  (2021-02-03T10:06:16Z)
• 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)
• Provably Good Batch Reinforcement Learning Without Great Exploration [51.51462608429621]
  Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Recent algorithms have shown promise but can still be overly optimistic in their expected outcomes. We show that a small modification to Bellman optimality and evaluation back-up to take a more conservative update can have much stronger guarantees.
  arXiv  Detail & Related papers  (2020-07-16T09:25:54Z)

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.