اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدComputational Benefits of Intermediate Rewards for Hierarchical Planning
153
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Many hierarchical reinforcement learning (RL) applications have empirically verified that incorporating prior knowledge in reward design improves convergence speed and practical performance. We attempt to quantify the computational benefits of hierarchical RL from a planning perspective under assumptions about the intermediate state and intermediate rewards frequently (but often implicitly) adopted in practice. Our approach reveals a trade-off between computational complexity and the pursuit of the shortest path in hierarchical planning: using intermediate rewards significantly reduces the computational complexity in finding a successful policy but does not guarantee to find the shortest path, whereas using sparse terminal rewards finds the shortest path at a significantly higher computational cost. We also corroborate our theoretical results with extensive experiments on the MiniGrid environments using Q-learning and other popular deep RL algorithms.
قيم البحث
اقرأ أيضاً
A classical problem in city-scale cyber-physical systems (CPS) is resource allocation under uncertainty. Typically, such problems are modeled as Markov (or semi-Markov) decision processes. While online, offline, and decentralized approaches have been
applied to such problems, they have difficulty scaling to large decision problems. We present a general approach to hierarchical planning that leverages structure in city-level CPS problems for resource allocation under uncertainty. We use the emergency response as a case study and show how a large resource allocation problem can be split into smaller problems. We then create a principled framework for solving the smaller problems and tackling the interaction between them. Finally, we use real-world data from Nashville, Tennessee, a major metropolitan area in the United States, to validate our approach. Our experiments show that the proposed approach outperforms state-of-the-art approaches used in the field of emergency response.
Todays automated vehicles lack the ability to cooperate implicitly with others. This work presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative planning using macro-actions for automated vehicles in heterogeneous envi
ronments. Based on cooperative modeling of other agents and Decoupled-UCT (a variant of MCTS), the algorithm evaluates the state-action-values of each agent in a cooperative and decentralized manner, explicitly modeling the interdependence of actions between traffic participants. Macro-actions allow for temporal extension over multiple time steps and increase the effective search depth requiring fewer iterations to plan over longer horizons. Without predefined policies for macro-actions, the algorithm simultaneously learns policies over and within macro-actions. The proposed method is evaluated under several conflict scenarios, showing that the algorithm can achieve effective cooperative planning with learned macro-actions in heterogeneous environments.
We present new planning and learning algorithms for RAE, the Refinement Acting Engine. RAE uses hierarchical operational models to perform tasks in dynamically changing environments. Our planning procedure, UPOM, does a UCT-like search in the space o
f operational models in order to find a near-optimal method to use for the task and context at hand. Our learning strategies acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. Our experimental results show that UPOM and our learning strategies significantly improve RAEs performance in four test domains using two different metrics: efficiency and success ratio.
In AI research, synthesizing a plan of action has typically used descriptive models of the actions that abstractly specify what might happen as a result of an action, and are tailored for efficiently computing state transitions. However, executing th
e planned actions has needed operational models, in which rich computational control structures and closed-loop online decision-making are used to specify how to perform an action in a complex execution context, react to events and adapt to an unfolding situation. Deliberative actors, which integrate acting and planning, have typically needed to use both of these models together -- which causes problems when attempting to develop the different models, verify their consistency, and smoothly interleave acting and planning. As an alternative, we define and implement an integrated acting-and-planning system in which both planning and acting use the same operational models. These rely on hierarchical task-oriented refinement methods offering rich control structures. The acting component, called Reactive Acting Engine (RAE), is inspired by the well-known PRS system. At each decision step, RAE can get advice from a planner for a near-optimal choice with respect to a utility function. The anytime planner uses a UCT-like Monte Carlo Tree Search procedure, called UPOM, (UCT Procedure for Operational Models), whose rollouts are simulations of the actors operational models. We also present learning strategies for use with RAE and UPOM that acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. We demonstrate the asymptotic convergence of UPOM towards optimal methods in static domains, and show experimentally that UPOM and the learning strategies significantly improve the acting efficiency and robustness.
In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design problem, or
close variants thereof, have been proposed in the literature. In this paper we build on the Optimal Rewards Framework of Singh et.al. that defines the optimal intrinsic reward function as one that when used by an RL agent achieves behavior that optimizes the task-specifying or extrinsic reward function. Previous work in this framework has shown how good intrinsic reward functions can be learned for lookahead search based planning agents. Whether it is possible to learn intrinsic reward functions for learning agents remains an open problem. In this paper we derive a novel algorithm for learning intrinsic rewards for policy-gradient based learning agents. We compare the performance of an augmented agent that uses our algorithm to provide additive intrinsic rewards to an A2C-based policy learner (for Atari games) and a PPO-based policy learner (for Mujoco domains) with a baseline agent that uses the same policy learners but with only extrinsic rewards. Our results show improved performance on most but not all of the domains.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
