اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMitigating Negative Side Effects via Environment Shaping
103
0
0.0
(
0
)
نشر من قبل
Sandhya Saisubramanian
تاريخ النشر
2021
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Agents operating in unstructured environments often produce negative side effects (NSE), which are difficult to identify at design time. While the agent can learn to mitigate the side effects from human feedback, such feedback is often expensive and the rate of learning is sensitive to the agents state representation. We examine how humans can assist an agent, beyond providing feedback, and exploit their broader scope of knowledge to mitigate the impacts of NSE. We formulate this problem as a human-agent team with decoupled objectives. The agent optimizes its assigned task, during which its actions may produce NSE. The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agents side effects, without affecting the agents ability to complete its assigned task. We present an algorithm to solve this problem and analyze its theoretical properties. Through experiments with human subjects, we assess the willingness of users to perform minor environment modifications to mitigate the impacts of NSE. Empirical evaluation of our approach shows that the proposed framework can successfully mitigate NSE, without affecting the agents ability to complete its assigned task.
قيم البحث
اقرأ أيضاً
Reduced models of large Markov decision processes accelerate planning by considering a subset of outcomes for each state-action pair. This reduction in reachable states leads to replanning when the agent encounters states without a precomputed action
during plan execution. However, not all states are suitable for replanning. In the worst case, the agent may not be able to reach the goal from the newly encountered state. Agents should be better prepared to handle such risky situations and avoid replanning in risky states. Hence, we consider replanning in states that are unsafe for deliberation as a negative side effect of planning with reduced models. While the negative side effects can be minimized by always using the full model, this defeats the purpose of using reduced models. The challenge is to plan with reduced models, but somehow account for the possibility of encountering risky situations. An agent should thus only replan in states that the user has approved as safe for replanning. To that end, we propose planning using a portfolio of reduced models, a planning paradigm that minimizes the negative side effects of planning using reduced models by alternating between different outcome selection approaches. We empirically demonstrate the effectiveness of our approach on three domains: an electric vehicle charging domain using real-world data from a university campus and two benchmark planning problems.
In high-dimensional state spaces, the usefulness of Reinforcement Learning (RL) is limited by the problem of exploration. This issue has been addressed using potential-based reward shaping (PB-RS) previously. In the present work, we introduce Final-V
olume-Preserving Reward Shaping (FV-RS). FV-RS relaxes the strict optimality guarantees of PB-RS to a guarantee of preserved long-term behavior. Being less restrictive, FV-RS allows for reward shaping functions that are even better suited for improving the sample efficiency of RL algorithms. In particular, we consider settings in which the agent has access to an approximate plan. Here, we use examples of simulated robotic manipulation tasks to demonstrate that plan-based FV-RS can indeed significantly improve the sample efficiency of RL over plan-based PB-RS.
The ability to create artificial intelligence (AI) capable of performing complex tasks is rapidly outpacing our ability to ensure the safe and assured operation of AI-enabled systems. Fortunately, a landscape of AI safety research is emerging in resp
onse to this asymmetry and yet there is a long way to go. In particular, recent simulation environments created to illustrate AI safety risks are relatively simple or narrowly-focused on a particular issue. Hence, we see a critical need for AI safety research environments that abstract essential aspects of complex real-world applications. In this work, we introduce the AI safety TanksWorld as an environment for AI safety research with three essential aspects: competing performance objectives, human-machine teaming, and multi-agent competition. The AI safety TanksWorld aims to accelerate the advancement of safe multi-agent decision-making algorithms by providing a software framework to support competitions with both system performance and safety objectives. As a work in progress, this paper introduces our research objectives and learning environment with reference code and baseline performance metrics to follow in a future work.
The RoboCup 2D Simulation League incorporates several challenging features, setting a benchmark for Artificial Intelligence (AI). In this paper we describe some of the ideas and tools around the development of our team, Gliders2012. In our descriptio
n, we focus on the evaluation function as one of our central mechanisms for action selection. We also point to a new framework for watching log files in a web browser that we release for use and further development by the RoboCup community. Finally, we also summarize results of the group and final matches we played during RoboCup 2012, with Gliders2012 finishing 4th out of 19 teams.
The MAPF problem is the fundamental problem of planning paths for multiple agents, where the key constraint is that the agents will be able to follow these paths concurrently without colliding with each other. Applications of MAPF include automated w
arehouses and autonomous vehicles. Research on MAPF has been flourishing in the past couple of years. Different MAPF research papers make different assumptions, e.g., whether agents can traverse the same road at the same time, and have different objective functions, e.g., minimize makespan or sum of agents actions costs. These assumptions and objectives are sometimes implicitly assumed or described informally. This makes it difficult to establish appropriate baselines for comparison in research papers, as well as making it difficult for practitioners to find the papers relevant to their concrete application. This paper aims to fill this gap and support researchers and practitioners by providing a unifying terminology for describing common MAPF assumptions and objectives. In addition, we also provide pointers to two MAPF benchmarks. In particular, we introduce a new grid-based benchmark for MAPF, and demonstrate experimentally that it poses a challenge to contemporary MAPF algorithms.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
