Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeliberative Acting, Online Planning and Learning with Hierarchical Operational Models
75
0
0.0
(
0
)
Added by
Sunandita Patra
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
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 the 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.
rate research
Read More
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 of 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.
Planning for robotic manipulation requires reasoning about the changes a robot can affect on objects. When such interactions can be modelled analytically, as in domains with rigid objects, efficient planning algorithms exist. However, in both domestic and industrial domains, the objects of interest can be soft, or deformable, and hard to model analytically. For such cases, we posit that a data-driven modelling approach is more suitable. In recent years, progress in deep generative models has produced methods that learn to `imagine plausible images from data. Building on the recent Causal InfoGAN generative model, in this work we learn to imagine goal-directed object manipulation directly from raw image data of self-supervised interaction of the robot with the object. After learning, given a goal observation of the system, our model can generate an imagined plan -- a sequence of images that transition the object into the desired goal. To execute the plan, we use it as a reference trajectory to track with a visual servoing controller, which we also learn from the data as an inverse dynamics model. In a simulated manipulation task, we show that separating the problem into visual planning and visual tracking control is more sample efficient and more interpretable than alternative data-driven approaches. We further demonstrate our approach on learning to imagine and execute in 3 environments, the final of which is deformable rope manipulation on a PR2 robot.
In this paper, we consider online planning in partially observable domains. Solving the corresponding POMDP problem is a very challenging task, particularly in an online setting. Our key contribution is a novel algorithmic approach, Simplified Information Theoretic Belief Space Planning (SITH-BSP), which aims to speed-up POMDP planning considering belief-dependent rewards, without compromising on the solutions accuracy. We do so by mathematically relating the simplified elements of the problem to the corresponding counterparts of the original problem. Specifically, we focus on belief simplification and use it to formulate bounds on the corresponding original belief-dependent rewards. These bounds in turn are used to perform branch pruning over the belief tree, in the process of calculating the optimal policy. We further introduce the notion of adaptive simplification, while re-using calculations between different simplification levels and exploit it to prune, at each level in the belief tree, all branches but one. Therefore, our approach is guaranteed to find the optimal solution of the original problem but with substantial speedup. As a second key contribution, we derive novel analytical bounds for differential entropy, considering a sampling-based belief representation, which we believe are of interest on their own. We validate our approach in simulation using these bounds and where simplification corresponds to reducing the number of samples, exhibiting a significant computational speedup while yielding the optimal solution.
Reinforcement learning (RL) in low-data and risk-sensitive domains requires performant and flexible deployment policies that can readily incorporate constraints during deployment. One such class of policies are the semi-parametric H-step lookahead policies, which select actions using trajectory optimization over a dynamics model for a fixed horizon with a terminal value function. In this work, we investigate a novel instantiation of H-step lookahead with a learned model and a terminal value function learned by a model-free off-policy algorithm, named Learning Off-Policy with Online Planning (LOOP). We provide a theoretical analysis of this method, suggesting a tradeoff between model errors and value function errors and empirically demonstrate this tradeoff to be beneficial in deep reinforcement learning. Furthermore, we identify the Actor Divergence issue in this framework and propose Actor Regularized Control (ARC), a modified trajectory optimization procedure. We evaluate our method on a set of robotic tasks for Offline and Online RL and demonstrate improved performance. We also show the flexibility of LOOP to incorporate safety constraints during deployment with a set of navigation environments. We demonstrate that LOOP is a desirable framework for robotics applications based on its strong performance in various important RL settings.
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 environments. 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.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
