Expert-Supervised Reinforcement Learning for Offline Policy Learning and
Evaluation
- URL: http://arxiv.org/abs/2006.13189v2
- Date: Fri, 30 Oct 2020 19:14:14 GMT
- Title: Expert-Supervised Reinforcement Learning for Offline Policy Learning and
Evaluation
- Authors: Aaron Sonabend-W, Junwei Lu, Leo A. Celi, Tianxi Cai, Peter Szolovits
- Abstract summary: We propose an Expert-Supervised RL (ESRL) framework which uses uncertainty quantification for offline policy learning.
In particular, we have three contributions: 1) the method can learn safe and optimal policies through hypothesis testing, 2) ESRL allows for different levels of risk averse implementations tailored to the application context, and 3) we propose a way to interpret ESRL's policy at every state through posterior distributions.
- Score: 21.703965401500913
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Offline Reinforcement Learning (RL) is a promising approach for learning
optimal policies in environments where direct exploration is expensive or
unfeasible. However, the adoption of such policies in practice is often
challenging, as they are hard to interpret within the application context, and
lack measures of uncertainty for the learned policy value and its decisions. To
overcome these issues, we propose an Expert-Supervised RL (ESRL) framework
which uses uncertainty quantification for offline policy learning. In
particular, we have three contributions: 1) the method can learn safe and
optimal policies through hypothesis testing, 2) ESRL allows for different
levels of risk averse implementations tailored to the application context, and
finally, 3) we propose a way to interpret ESRL's policy at every state through
posterior distributions, and use this framework to compute off-policy value
function posteriors. We provide theoretical guarantees for our estimators and
regret bounds consistent with Posterior Sampling for RL (PSRL). Sample
efficiency of ESRL is independent of the chosen risk aversion threshold and
quality of the behavior policy.
Related papers
- SAD: State-Action Distillation for In-Context Reinforcement Learning under Random Policies [2.52299400625445]
State-Action Distillation (SAD) generates a remarkable pretraining dataset guided solely by random policies.
SAD outperforms the best baseline by 180.86% in the offline evaluation and by 172.8% in the online evaluation.
arXiv Detail & Related papers (2024-10-25T21:46:25Z) - Robust off-policy Reinforcement Learning via Soft Constrained Adversary [0.7583052519127079]
We introduce an f-divergence constrained problem with the prior knowledge distribution.
We derive two typical attacks and their corresponding robust learning frameworks.
Results demonstrate that our proposed methods achieve excellent performance in sample-efficient off-policy RL.
arXiv Detail & Related papers (2024-08-31T11:13:33Z) - Uncertainty-aware Distributional Offline Reinforcement Learning [26.34178581703107]
offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data.
We propose an uncertainty-aware distributional offline RL method to simultaneously address both uncertainty and environmentality.
Our method is rigorously evaluated through comprehensive experiments in both risk-sensitive and risk-neutral benchmarks, demonstrating its superior performance.
arXiv Detail & Related papers (2024-03-26T12:28:04Z) - Offline Reinforcement Learning with On-Policy Q-Function Regularization [57.09073809901382]
We deal with the (potentially catastrophic) extrapolation error induced by the distribution shift between the history dataset and the desired policy.
We propose two algorithms taking advantage of the estimated Q-function through regularizations, and demonstrate they exhibit strong performance on the D4RL benchmarks.
arXiv Detail & Related papers (2023-07-25T21:38:08Z) - Counterfactual Explanation Policies in RL [3.674863913115432]
COUNTERPOL is the first framework to analyze Reinforcement Learning policies using counterfactual explanations.
We establish a theoretical connection between Counterpol and widely used trust region-based policy optimization methods in RL.
arXiv Detail & Related papers (2023-07-25T01:14:56Z) - COptiDICE: Offline Constrained Reinforcement Learning via Stationary
Distribution Correction Estimation [73.17078343706909]
offline constrained reinforcement learning (RL) problem, in which the agent aims to compute a policy that maximizes expected return while satisfying given cost constraints, learning only from a pre-collected dataset.
We present an offline constrained RL algorithm that optimize the policy in the space of the stationary distribution.
Our algorithm, COptiDICE, directly estimates the stationary distribution corrections of the optimal policy with respect to returns, while constraining the cost upper bound, with the goal of yielding a cost-conservative policy for actual constraint satisfaction.
arXiv Detail & Related papers (2022-04-19T15:55:47Z) - Combing Policy Evaluation and Policy Improvement in a Unified
f-Divergence Framework [33.90259939664709]
We study the f-divergence between learning policy and sampling policy and derive a novel DRL framework, termed f-Divergence Reinforcement Learning (FRL)
The FRL framework achieves two advantages: (1) policy evaluation and policy improvement processes are derived simultaneously by f-divergence; (2) overestimation issue of value function are alleviated.
arXiv Detail & Related papers (2021-09-24T10:20:46Z) - 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) - 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) - 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.