In recent years deep neural networks have been successfully applied to the domains of reinforcement learning \cite{bengio2009learning,krizhevsky2012imagenet,hinton2006reducing}. Deep reinforcement learning \cite{mnih2015human} is reported to have the advantage of learning effective policies directly from high-dimensional sensory inputs over traditional agents. However, within the scope of the literature, there is no fundamental change or improvement on the existing training framework. Here we propose a novel training framework that is conceptually comprehensible and potentially easy to be generalized to all feasible algorithms for reinforcement learning. We employ Monte-carlo sampling to achieve raw data inputs, and train them in batch to achieve Markov decision process sequences and synchronously update the network parameters instead of experience replay. This training framework proves to optimize the unbiased approximation of loss function whose estimation exactly matches the real probability distribution data inputs follow, and thus have overwhelming advantages of sample efficiency and convergence rate over existing deep reinforcement learning after evaluating it on both discrete action spaces and continuous control problems. Besides, we propose several algorithms embedded with our new framework to deal with typical discrete and continuous scenarios. These algorithms prove to be far more efficient than their original versions under the framework of deep reinforcement learning, and provide examples for existing and future algorithms to generalize to our new framework.
In partially observable reinforcement learning, offline training gives access to latent information which is not available during online training and/or execution, such as the system state. Asymmetric actor-critic methods exploit such information by training a history-based policy via a state-based critic. However, many asymmetric methods lack theoretical foundation, and are only evaluated on limited domains. We examine the theory of asymmetric actor-critic methods which use state-based critics, and expose fundamental issues which undermine the validity of a common variant, and limit its abili…
Inria（法国国家信息与自动化研究所）；Université Paris Saclay（巴黎萨克雷大学）；FAIR（脸书人工智能研究院）
In multi-goal reinforcement learning (RL) settings, the reward for each goal is sparse, and located in a small neighborhood of the goal. In large dimension, the probability of reaching a reward vanishes and the agent receives little learning signal. Methods such as Hindsight Experience Replay (HER) tackle this issue by also learning from realized but unplanned-for goals. But HER is known to introduce bias, and can converge to low-return policies by overestimating chancy outcomes. First, we vindicate HER by proving that it is actually unbiased in deterministic environments, such as many optimal…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；C3.ai Digital Transformation Institute（C3.ai数字化转型研究院）
We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are useful for very large MDPs, including lookahead, function approximation, and gradient descent. Specifically, we analyze two algorithms; the first algorithm involves a least squares approach where a new set of weights associated with feature vectors is obtained via least squares minimization at each iteration and the second algorithm involves a two-time-scale sto…
Real-time bidding is the new paradigm of programmatic advertising. An advertiser wants to make the intelligent choice of utilizing a \textbf{Demand-Side Platform} to improve the performance of their ad campaigns. Existing approaches are struggling to provide a satisfactory solution for bidding optimization due to stochastic bidding behavior. In this paper, we proposed a multi-agent reinforcement learning architecture for RTB with functional optimization. We designed four agents bidding environment: three Lagrange-multiplier based functional optimization agents and one baseline agent (without a…
Dealing with sparse rewards is a long-standing challenge in reinforcement learning (RL). Hindsight Experience Replay (HER) addresses this problem by reusing failed trajectories for one goal as successful trajectories for another. This allows for both a minimum density of reward and for generalization across multiple goals. However, this strategy is known to result in a biased value function, as the update rule underestimates the likelihood of bad outcomes in a stochastic environment. We propose an asymptotically unbiased importance-sampling-based algorithm to address this problem without sacri…
Despite the empirical success of meta reinforcement learning (meta-RL), there are still a number poorly-understood discrepancies between theory and practice. Critically, biased gradient estimates are almost always implemented in practice, whereas prior theory on meta-RL only establishes convergence under unbiased gradient estimates. In this work, we investigate such a discrepancy. In particular, (1) We show that unbiased gradient estimates have variance $Θ(N)$ which linearly depends on the sample size $N$ of the inner loop updates; (2) We propose linearized score function (LSF) gradient estima…
Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty arises from stochastic environments and must be accounted for in risk-sensitive applications. We highlight the challenges involved in simultaneously estimating both of them, and propose a framework for disentangling and estimating these uncertainties on learned Q-values. We derive unbiased estimators of these uncertainties and introduce an uncertainty-aware DQN algorithm, which we show exhibits safe learning behavior a…
Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE；Technology Innovation Institute, Abu Dhabi, UAE；Department of Robotics, Khalifa University, Abu Dhabi, UAE
FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
College of Software, Nankai University（南开大学软件学院）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；IIIS, Tsinghua University（清华大学智能系统与信息工程研究院）；Zhongguancun Academy, Beijing, China（北京中关村学院）
Off-policy evaluation is a key component of reinforcement learning which evaluates a target policy with offline data collected from behavior policies. It is a crucial step towards safe reinforcement learning and has been used in advertisement, recommender systems and many other applications. In these applications, sometimes the offline data is collected from multiple behavior policies. Previous works regard data from different behavior policies equally. Nevertheless, some behavior policies are better at producing good estimators while others are not. This paper starts with discussing how to co…
University of Alberta（阿尔伯塔大学）；Stanford University（斯坦福大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical for policy evaluation, but existing estimators that reuse old data introduce large bias such that we can not obtain a valid confidence interval. Inspired from a related field called survey sampling, we introduce a variant of the doubly robust (DR) estimator, called the regression-assisted DR estimator, that can incorporate the past data without introducing a large bias. The estimator unifies several existi…
Low-thrust trajectory design and in-flight control remain two of the most challenging topics for new-generation satellite operations. Most of the solutions currently implemented are based on reference trajectories and lead to sub-optimal fuel usage. Other solutions are based on simple guidance laws that need to be updated periodically, increasing the cost of operations. Whereas some optimization strategies leverage Artificial Intelligence methods, all of the approaches studied so far need either previously generated data or a strong a priori knowledge of the satellite dynamics. This study uses…
Clicks on rankings suffer from position-bias: generally items on lower ranks are less likely to be examined - and thus clicked - by users, in spite of their actual preferences between items. The prevalent approach to unbiased click-based learning-to-rank (LTR) is based on counterfactual inverse-propensity-scoring (IPS) estimation. In contrast with general reinforcement learning, counterfactual doubly-robust (DR) estimation has not been applied to click-based LTR in previous literature. In this paper, we introduce a novel DR estimator that is the first DR approach specifically designed for posi…
SPOTting the Future: Lookahead Explanations for Deep Reinforcement Learning
Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem（耶路撒冷希伯来大学贝林计算机科学与工程学院）；Hebrew University Business School, Data Science Department, The Hebrew University of Jerusalem（耶路撒冷希伯来大学希伯来大学商学院数据科学系）
Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into the future. In this setting, a model-based agent with a sufficiently accurate model can avoid unsafe states. We devise a model-based algorithm that heavily penalizes unsafe trajectories, and derive guarantees that our algorithm can avoid unsafe states under certain assumptions. Experiments demonstra…
The past decade has seen the rapid development of Reinforcement Learning, which acquires impressive performance with numerous training resources. However, one of the greatest challenges in RL is generalization efficiency (i.e., generalization performance in a unit time). This paper proposes a framework of Active Reinforcement Learning (ARL) over MDPs to improve generalization efficiency in a limited resource by instance selection. Given a number of instances, the algorithm chooses out valuable instances as training sets while training the policy, thereby costing fewer resources. Unlike existin…
University of Freiburg（弗莱堡大学）；University of Technology Nuremberg（纽伦堡工业大学）
Accurate value estimates are important for off-policy reinforcement learning. Algorithms based on temporal difference learning typically are prone to an over- or underestimation bias building up over time. In this paper, we propose a general method called Adaptively Calibrated Critics (ACC) that uses the most recent high variance but unbiased on-policy rollouts to alleviate the bias of the low variance temporal difference targets. We apply ACC to Truncated Quantile Critics, which is an algorithm for continuous control that allows regulation of the bias with a hyperparameter tuned per environme…
University of Galway（戈尔韦大学）；Vrije Universiteit Brussel（布鲁塞尔自由大学）；City of Amsterdam（阿姆斯特丹市）
In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from a single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. Making decisions using just the expected future returns -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Therefore, we should use the distribution over expected future returns…
This note aims to provide a basic intuition on the concept of filtrations as used in the context of reinforcement learning (RL). Filtrations are often used to formally define RL problems, yet their implications might not be eminent for those without a background in measure theory. Essentially, a filtration is a construct that captures partial knowledge up to time $t$, without revealing any future information that has already been simulated, yet not revealed to the decision-maker. We illustrate this with simple examples from the finance domain on both discrete and continuous outcome spaces. Fur…
The exploration--exploitation trade-off in reinforcement learning (RL) is a well-known and much-studied problem that balances greedy action selection with novel experience, and the study of exploration methods is usually only considered in the context of learning the optimal policy for a single learning task. However, in the context of online task transfer, where there is a change to the task during online operation, we hypothesize that exploration strategies that anticipate the need to adapt to future tasks can have a pronounced impact on the efficiency of transfer. As such, we re-examine the…
Stanford University（斯坦福大学）；University of Pennsylvania（宾夕法尼亚大学）
A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -- \textit{uniformly} outperforming a conservative policy (adaptively estimated from all data observed thus far), up to a per-episode exploration budget. We design a novel algorithm that uses a UCB reinforcement learning policy for exploration, but overrides it as needed to satisfy our exploration constraint with high probability. Importantly, to ensure unbiased exploration across the state space, our algorithm adapti…
Brown University（布朗大学）；Computer Science Department（计算机科学系）；Carney Institute for Brain Science（卡尼脑科学研究所）；Providence, RI 02912, USA（美国罗得岛州普罗维登斯市 02912）
A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs. By generalizing across different inputs, information learned for one input can be immediately reused for improving predictions for another input. Reusing information allows an agent to compute an optimal decision-making strategy using less data. State representation is a key element of the generalization process, compressing a high-dimensional input space into a low-dimensional latent state space. This article analyzes properties of different latent state spaces, leading to ne…
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）；Didi Voyager Labs, DiDi Autonomous Driving（滴滴自动驾驶沃芽实验室）；College of AI, Tsinghua University（清华大学人工智能学院）
The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors, changes in the real-world system dynamics over time, and adversarial disturbances. Robust RL is typically formulated as a max-min problem, where the objective is to learn the policy that maximizes the value against the worst possible models that lie in an uncertainty set. In this work, we propose a robust RL algorithm called Robust Fitted Q-Iteration (RFQI), whic…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；PHENIKAA University（phenikaa大学）；Nanyang Technological University（南洋理工大学）
Future Internet involves several emerging technologies such as 5G and beyond 5G networks, vehicular networks, unmanned aerial vehicle (UAV) networks, and Internet of Things (IoTs). Moreover, future Internet becomes heterogeneous and decentralized with a large number of involved network entities. Each entity may need to make its local decision to improve the network performance under dynamic and uncertain network environments. Standard learning algorithms such as single-agent Reinforcement Learning (RL) or Deep Reinforcement Learning (DRL) have been recently used to enable each network entity a…
Reinforcement learning (RL) commonly assumes access to well-specified reward functions, which many practical applications do not provide. Instead, recently, more work has explored learning what to do from interacting with humans. So far, most of these approaches model humans as being (nosily) rational and, in particular, giving unbiased feedback. We argue that these models are too simplistic and that RL researchers need to develop more realistic human models to design and evaluate their algorithms. In particular, we argue that human models have to be personal, contextual, and dynamic. This pap…
