Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of current users for information that will lead to better decisions in the future. Recently, concerns have been raised about whether the process of exploration could be viewed as unfair, placing too much burden on certain individuals or groups. Motivated by these concerns, we initiate the study of the externalities of exploration - the undesirable side effects that the presence of one party may impose on another - under the linear contextual bandits model. We introduce the notion of a group externality, measuring the extent to which the presence of one population of users impacts the rewards of another. We show that this impact can in some cases be negative, and that, in a certain sense, no algorithm can avoid it. We then study externalities at the individual level, interpreting the act of exploration as an externality imposed on the current user of a system by future users. This drives us to ask under what conditions inherent diversity in the data makes explicit exploration unnecessary. We build on a recent line of work on the smoothed analysis of the greedy algorithm that always chooses the action that currently looks optimal, improving on prior results to show that a greedy approach almost matches the best possible Bayesian regret rate of any other algorithm on the same problem instance whenever the diversity conditions hold, and that this regret is at most $\tilde{O}(T^{1/3})$. Returning to group-level effects, we show that under the same conditions, negative group externalities essentially vanish under the greedy algorithm. Together, our results uncover a sharp contrast between the high externalities that exist in the worst case, and the ability to remove all externalities if the data is sufficiently diverse.
Contextual bandits have the same exploration-exploitation trade-off as standard multi-armed bandits. On adding positive externalities that decay with time, this problem becomes much more difficult as wrong decisions at the start are hard to recover from. We explore existing policies in this setting and highlight their biases towards the inherent reward matrix. We propose a rejection based policy that achieves a low regret irrespective of the structure of the reward probability matrix.
In continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems. Conversely, evolutionary and developmental methods focusing on exploration like Novelty Search, Quality-Diversity or Goal Exploration Processes explore more robustly but are less efficient at fine-tuning policies using gradient descent. In this paper, we present the GEP-PG approach, taking the best of both worlds by sequentially combining a Goal Exploration Process and two variants of DDPG. We study the learning performance…
Exploration is a key challenge in Reinforcement Learning, especially in long-horizon, deceptive and sparse-reward environments. For such applications, population-based approaches have proven effective. Methods such as Quality-Diversity deals with this by encouraging novel solutions and producing a diversity of behaviours. However, these methods are driven by either undirected sampling (i.e. mutations) or use approximated gradients (i.e. Evolution Strategies) in the parameter space, which makes them highly sample-inefficient. In this paper, we propose a model-based Quality-Diversity approach. I…
InstaDeep；Imperial College London（帝国理工学院）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）
A fascinating aspect of nature lies in its ability to produce a large and diverse collection of organisms that are all high-performing in their niche. By contrast, most AI algorithms focus on finding a single efficient solution to a given problem. Aiming for diversity in addition to performance is a convenient way to deal with the exploration-exploitation trade-off that plays a central role in learning. It also allows for increased robustness when the returned collection contains several working solutions to the considered problem, making it well-suited for real applications such as robotics. …
Université de Paris（巴黎大学）；Ochanomizu University（御茶水女子大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
By combining Genetic Programming, MAP-Elites and Covariance Matrix Adaptation Evolution Strategy, we demonstrate very high success rates in Symbolic Regression problems. MAP-Elites is used to improve exploration while preserving diversity and avoiding premature convergence and bloat. Then, a Covariance Matrix Adaptation-Evolution Strategy is used to evaluate free scalars through a non-gradient-based black-box optimizer. Although this evaluation approach is not computationally scalable to high dimensional problems, our algorithm is able to find exactly most of the $31$ targets extracted from th…
Binghamton University（宾汉姆顿大学）；Yantai University（烟台大学）；Assured Information Security（Assured Information Security（Assured Information Security公司））
We study an important yet under-addressed problem of quickly and safely improving policies in online reinforcement learning domains. As its solution, we propose a novel exploration strategy - diverse exploration (DE), which learns and deploys a diverse set of safe policies to explore the environment. We provide DE theory explaining why diversity in behavior policies enables effective exploration without sacrificing exploitation. Our empirical study shows that an online policy improvement algorithm framework implementing the DE strategy can achieve both fast policy improvement and safe online p…
Harvard University（哈佛大学）；Microsoft Research NYC（微软纽约研究院）；Microsoft Research, New York（微软纽约研究院）；Carnegie Mellon University（卡内基梅隆大学）
Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of current users in order to gain information that will lead to better decisions in the future. While necessary in the worst case, explicit exploration has a number of disadvantages compared to the greedy algorithm that always "exploits" by choosing an action that currently looks optimal. We ask under what conditions inherent diversity in the data makes explicit exploration unnecessary. We build on a recent line of work o…
Sorbonne Université（索邦大学）；Institut des Systèmes Intelligents et de Robotique（智能系统与机器人研究所）；Softbank Robotics Europe（软银机器人欧洲公司）
In the Reinforcement Learning (RL) framework, the learning is guided through a reward signal. This means that in situations of sparse rewards the agent has to focus on exploration, in order to discover which action, or set of actions leads to the reward. RL agents usually struggle with this. Exploration is the focus of Quality-Diversity (QD) methods. In this thesis, we approach the problem of sparse rewards with these algorithms, and in particular with Novelty Search (NS). This is a method that only focuses on the diversity of the possible policies behaviors. The first part of the thesis focus…
Microsoft Research（微软研究院）；University of Pennsylvania（宾夕法尼亚大学）；University of Minnesota（明尼苏达大学）
It is common in recommendation systems that users both consume and produce information as they make strategic choices under uncertainty. While a social planner would balance "exploration" and "exploitation" using a multi-armed bandit algorithm, users' incentives may tilt this balance in favor of exploitation. We consider Bayesian Exploration: a simple model in which the recommendation system (the "principal") controls the information flow to the users (the "agents") and strives to incentivize exploration via information asymmetry. A single round of this model is a version of a well-known "Baye…
Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Q-learning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects a…
We propose PESA, a novel approach combining Particle Swarm Optimisation (PSO), Evolution Strategy (ES), and Simulated Annealing (SA) in a hybrid Algorithm, inspired from reinforcement learning. PESA hybridizes the three algorithms by storing their solutions in a shared replay memory. Next, PESA applies prioritized replay to redistribute data between the three algorithms in frequent form based on their fitness and priority values, which significantly enhances sample diversity and algorithm exploration. Additionally, greedy replay is used implicitly within SA to improve PESA exploitation close t…
University of California San Diego（加州大学圣地亚哥分校）；Shenzhen Research Institute of Big Data（深圳大数据研究院）
The diversity of intrinsic qualities of multimedia entities tends to impede their effective retrieval. In a SelfLearning Search Engine architecture, the subtle nuances of human perceptions and deep knowledge are taught and captured through unsupervised reinforcement learning, where the degree of reinforcement may be suitably calibrated. Such architectural paradigm enables indexes to evolve naturally while accommodating the dynamic changes of user interests. It operates by continuously constructing indexes over time, while injecting progressive improvement in search performance. For search oper…
Quality Diversity (QD) algorithms such as MAP-Elites are a class of optimisation techniques that attempt to find a set of high-performing points from an objective function while enforcing behavioural diversity of the points over one or more interpretable, user chosen, feature functions. In this paper we propose the Bayesian Optimisation of Elites (BOP-Elites) algorithm that uses techniques from Bayesian Optimisation to explicitly model both quality and diversity with Gaussian Processes. By considering user defined regions of the feature space as 'niches' our task is to find the optimal solutio…
The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Tencent AI Lab（腾讯人工智能实验室）
Machine learning algorithms minimizing the average training loss usually suffer from poor generalization performance due to the greedy exploitation of correlations among the training data, which are not stable under distributional shifts. It inspires various works for domain generalization (DG), where a series of methods, such as Causal Matching and FISH, work by pairwise domain operations. They would need $O(n^2)$ pairwise domain operations with $n$ domains, where each one is often highly expensive. Moreover, while a common objective in the DG literature is to learn invariant representations …
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）
