Paper proposes a sequential statistical test for comparing imitation learning policies with near-optimal stopping.
problem Challenges in rigorously comparing imitation learning policies due to small sample sizes and potential p-hacking.
method Sequential statistical test that adapts the number of trials based on intermediate results, achieving near-optimal stopping.
result Reduces the number of evaluation trials by up to 32% compared to state-of-the-art baselines, saving significant time and effort.
New framework estimates treatment effects based on preferences.
problem Estimating treatment effects with flexible outcomes.
method Preference-based Conditional Treatment Effect (CPTE) framework.
result CPTE provides interpretable targets and new identifiability conditions.
We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps av…
In this paper we consider the basic version of Reinforcement Learning (RL) that involves computing optimal data driven (adaptive) policies for Markovian decision process with unknown transition probabilities. We provide a brief survey of the state of the art of the area and we compare the performance of the classic UCB…
Bayesian method infers contextual bandit policies robustly.
problem Inference of contextual bandit policies in small sample sizes.
method Empirical likelihood for Bayesian inference.
result Accurate uncertainty measurements and policy comparison.
This paper focuses on stochastic orders and its applications : policy limits and deductibles. Further, many applications and some examples are given : comparison of two families of copulas, individual and collective risk model, reinsurance contracts and dependent portfolios increase risk. More precisely, we propose a n…
Adaptive reduction scheme approximates optimal policy in regularized MDPs.
problem Finding near optimal policy in regularized MDPs with biased solutions.
method Adaptive reduction of regularization parameter λ to approximate optimal policy.
result Iteration complexity reduced for obtaining ε-optimal policy.
News on inflation and monetary policy impacts US household inflation expectations.
problem Understanding how news affects inflation expectations.
method Monthly disaggregated US data from 1978 to 2016, controlling for various factors.
result News on rising inflation and easier monetary policy has a stronger impact on inflation expectations.
Recent successful deep reinforcement learning algorithms, such as Trust Region Policy Optimization (TRPO) or Proximal Policy Optimization (PPO), are fundamentally variations of conservative policy iteration (CPI). These algorithms iterate policy evaluation followed by a softened policy improvement step. As so, they are…
Rank aggregation based on pairwise comparisons over a set of items has a wide range of applications. Although considerable research has been devoted to the development of rank aggregation algorithms, one basic question is how to efficiently collect a large amount of high-quality pairwise comparisons for the ranking pur…
We study the problem of learning Markov decision processes with finite state and action spaces when the transition probability distributions and loss functions are chosen adversarially and are allowed to change with time. We introduce an algorithm whose regret with respect to any policy in a comparison class grows as t…
Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcem…
Adaptive optimal control of nonlinear dynamic systems with deterministic and known dynamics under a known undiscounted infinite-horizon cost function is investigated. Policy iteration scheme initiated using a stabilizing initial control is analyzed in solving the problem. The convergence of the iterations and the optim…
We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on several approximate variations of the Policy Iteration algorithm: Approximate Policy Iteration, Conservative Policy Iteration (CPI), a natural adaptation of the Policy Search by Dynamic Programming a…
Contextual policy search (CPS) is a class of multi-task reinforcement learning algorithms that is particularly useful for robotic applications. A recent state-of-the-art method is Contextual Covariance Matrix Adaptation Evolution Strategies (C-CMA-ES). It is based on the standard black-box optimization algorithm CMA-ES…
Revisits PPO design choices, exposing failure modes and proposing alternatives.
problem Failure modes of standard PPO in new environments.
method Revisits standard PPO design choices, exposes failure modes, and proposes alternative approaches.
result Alternative design choices prevent failure modes in new environments.
Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline policy in the uncertain state-action pairs, in order to control the variance on th…
RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST) for PO with mediator feedback.
problem Policy Optimization in continuous control tasks.
method RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST) for regret minimization in PO.
result Achieving constant regret under certain circumstances in PO with mediator feedback.
As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the po…
DBQPG improves policy gradient estimation with fewer samples.
problem Accurate policy gradient estimation with limited samples.
method Deep Bayesian Quadrature Policy Gradient (DBQPG).
result DBQPG provides more accurate and less variable gradient estimates.
Examines how central bank policies affect stock markets and asset prices.
problem Understanding the impact of monetary policy on stock markets and asset prices.
method Used Taylor rule equations to analyze data from 1990 to 2020 for US and UK, testing with various econometric methods.
result Monetary policy can explain asset price volatility and output gap better than just inflation rate.
The paper analyzes RLHF with human feedback and provides convergence results for MLE and pessimistic MLE.
problem Improving RLHF with human feedback from pairwise or K-wise comparisons. method Theoretical framework for RLHF with convergence analysis of MLE and pessimistic MLE.
result MLE fails but pessimistic MLE provides improved policies under certain coverage assumptions.
Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervised learning problem, have been proposed recently. Finding good policies with such methods requires not only an appropriate classifier, but also reliable e…
Novel methods generate diverse policies in reinforcement learning.
problem Generating diverse policies in reinforcement learning.
method Constrained optimization perspective, introducing new metrics, and novel policy generation methods.
result Improved novelty and performance of generated policies.
MAGE optimizes policies using action gradients from model-based learning.
problem Lack of direct gradient information from critics in actor-critic methods.
method Model-based actor-critic algorithm that learns action-value gradient.
result MAGE outperforms model-free and model-based baselines on continuous control tasks.
Unified framework for analyzing pessimism in off-policy learning with regularized importance sampling.
problem High variance in importance weighting for off-policy learning.
method Unified PAC-Bayesian study of pessimism with regularized importance sampling.
result Derivation of a tractable PAC-Bayesian generalization bound for common importance weight regularizations.
In artificial intelligence, we often specify tasks through a reward function. While this works well in some settings, many tasks are hard to specify this way. In deep reinforcement learning, for example, directly specifying a reward as a function of a high-dimensional observation is challenging. Instead, we present an …
As the most successful variant and improvement for Trust Region Policy Optimization (TRPO), proximal policy optimization (PPO) has been widely applied across various domains with several advantages: efficient data utilization, easy implementation, and good parallelism. In this paper, a first-order gradient reinforcemen…
ReSkill reconciles RL skill creation with policy optimization.
problem RL policies lack reusable strategies across tasks.
method Integrates skill creation into RL loop with three mechanisms.
result Consistently outperforms existing methods, especially on unseen tasks.
EPIC quantifies reward differences without policy optimization.
problem Distinguishing reward function quality from policy optimization issues.
method EPIC distance to compare reward functions directly.
result EPIC bounds policy training success and regret.
This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's …
Unified stopping rules ensure accurate policies in contextual learning.
problem Stopping data collection to ensure accurate policies in personalized decision problems.
method Developed unified stopping rules based on GLR statistics for pairwise action comparisons.
result Unified stopping rules achieve target precision with fewer samples than benchmarks.
We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function;…
Proposes a new policy gradient algorithm to improve reinforcement learning efficiency and stability.
problem Inefficiency and instability of DDPG in practical applications, and difficulty in controlling Q estimation bias and variance.
method Introduces a Regularly Updated Deterministic (RUD) policy gradient algorithm.
result The RUD algorithm makes better use of new data and has lower Q value variance, leading to improved performance.
We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of applications including health-care policy and Internet advertising. A central task is eval…
Paper uses RL to optimize insurance pricing on PCWs, improving efficiency and adaptability.
problem Optimizing pricing on price comparison websites while balancing competitiveness and profitability.
method Integrates model-based and model-free reinforcement learning methods for dynamic pricing.
result Hybrid RL agent outperforms existing methods in sample efficiency and cumulative reward.
This paper uses deep reinforcement learning to optimize stock portfolios considering transaction costs and risks.
problem Optimizing stock portfolios with transaction costs and risks.
method Formulated stock portfolio optimization as a reinforcement learning problem, applied DDPG, GDPG, and PPO algorithms, and used Wavelet Transform.
result DDPG and GDPG algorithms outperformed PPO in continuous action space.
Bayesian optimization improves policy search in reinforcement learning.
problem Finding optimal policies with high variance estimates from random samples.
method Develops an algorithm combining Bayesian optimization and policy gradients.
result Improves sample complexity and reduces variance in empirical evaluations.
This work characterizes reward function partial identifiability and its impact on policy optimization.
problem Reward function partial identifiability in complex tasks.
method Formal characterisation of partial identifiability using various reward learning data sources.
result Unified framework for comparing data sources and downstream tasks by their invariances.
RPI combines imitation and reinforcement learning to improve policies efficiently.
problem High sample complexity in reinforcement learning.
method Active interleaving between imitation and reinforcement learning, using oracle queries for exploration.
result RPI outperforms existing methods across various domains.
SPReD uses uncertainty to decide imitation from demonstrations.
problem Learning from sparse rewards with few demonstrations.
method Ensemble methods to model Q-value distributions, probabilistic and advantage-based uncertainty quantification.
result Significant gains in reinforcement learning across multiple tasks.
This paper proposes an online tree-based Bayesian approach for reinforcement learning. For inference, we employ a generalised context tree model. This defines a distribution on multivariate Gaussian piecewise-linear models, which can be updated in closed form. The tree structure itself is constructed using the cover tr…
Study uses PPLs to model and forecast COVID-19 spread and policy interventions.
problem Forecast and control the spread of COVID-19 using policy interventions.
method Compartmental models, probabilistic programming, inference, greedy algorithm.
result Optimal series of policy interventions can control the infected population.
Develops a support-aware framework for reserve-policy selection in advertising markets.
problem Log-based reserve-price evaluation risks weak support and subgroup harm.
method Support-aware offline decision framework converting logged evidence into certified policies.
result Preserves the best gate-passing policy while eliminating only policies with certified regret.
We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance relative to the Bayes optimal policy, with a lower computational complexity. Th…
This work benchmarks MARL algorithms in cooperative tasks.
problem Lack of evaluation tasks and criteria for comparing MARL algorithms.
method Systematic evaluation of three MARL algorithm classes in diverse cooperative tasks.
result Insights into the effectiveness of different learning approaches.
In multi-objective decision planning and learning, much attention is paid to producing optimal solution sets that contain an optimal policy for every possible user preference profile. We argue that the step that follows, i.e, determining which policy to execute by maximising the user's intrinsic utility function over t…
Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has significantly enhanced performances on many image recognition tasks. However, its sea…