Creating a domain model, even for classical, domain-independent planning, is a notoriously hard knowledge-engineering task. A natural approach to solve this problem is to learn a domain model from observations. However, model learning approaches frequently do not provide safety guarantees: the learned model may assume actions are applicable when they are not, and may incorrectly capture actions' effects. This may result in generating plans that will fail when executed. In some domains such failures are not acceptable, due to the cost of failure or inability to replan online after failure. In such settings, all learning must be done offline, based on some observations collected, e.g., by some other agents or a human. Through this learning, the task is to generate a plan that is guaranteed to be successful. This is called the model-free planning problem. Prior work proposed an algorithm for solving the model-free planning problem in classical planning. However, they were limited to learning grounded domains, and thus they could not scale. We generalize this prior work and propose the first safe model-free planning algorithm for lifted domains. We prove the correctness of our approach, and provide a statistical analysis showing that the number of trajectories needed to solve future problems with high probability is linear in the potential size of the domain model. We also present experiments on twelve IPC domains showing that our approach is able to learn the real action model in all cases with at most two trajectories.
This content will become publicly available on June 27, 2024
Learning Safe Numeric Action Models
Powerful domain-independent planners have been developed to solve various types of planning problems. These planners often require a model of the acting agent's actions, given in some planning domain description language. Yet obtaining such an action model is a notoriously hard task. This task is even more challenging in mission-critical domains, where a trial-and-error approach to learning how to act is not an option. In such domains, the action model used to generate plans must be safe, in the sense that plans generated with it must be applicable and achieve their goals. Learning safe action models for planning has been recently explored for domains in which states are sufficiently described with Boolean variables. In this work, we go beyond this limitation and propose the NSAM algorithm. NSAM runs in time that is polynomial in the number of observations and, under certain conditions, is guaranteed to return safe action models. We analyze its worst-case sample complexity, which may be intractable for some domains. Empirically, however, NSAM can quickly learn a safe action model that can solve most problems in the domain.
more »
« less
- NSF-PAR ID:
- 10467339
- Publisher / Repository:
- AAAI
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 37
- Issue:
- 10
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 12079 to 12086
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
null (Ed.)The objective of this work is to augment the basic abilities of a robot by learning to use sensorimotor primitives to solve complex long-horizon manipulation problems. This requires flexible generative planning that can combine primitive abilities in novel combinations and, thus, generalize across a wide variety of problems. In order to plan with primitive actions, we must have models of the actions: under what circumstances will executing this primitive successfully achieve some particular effect in the world? We use, and develop novel improvements to, state-of-the-art methods for active learning and sampling. We use Gaussian process methods for learning the constraints on skill effectiveness from small numbers of expensive-to-collect training examples. In addition, we develop efficient adaptive sampling methods for generating a comprehensive and diverse sequence of continuous candidate control parameter values (such as pouring waypoints for a cup) during planning. These values become end-effector goals for traditional motion planners that then solve for a full robot motion that performs the skill. By using learning and planning methods in conjunction, we take advantage of the strengths of each and plan for a wide variety of complex dynamic manipulation tasks. We demonstrate our approach in an integrated system, combining traditional robotics primitives with our newly learned models using an efficient robot task and motion planner. We evaluate our approach both in simulation and in the real world through measuring the quality of the selected primitive actions. Finally, we apply our integrated system to a variety of long-horizon simulated and real-world manipulation problems.more » « less
-
Integrating Symbolic Planning and Reinforcement Learning for Following Temporal Logic SpecificationsTeaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments is a challenging problem. We consider that user defines every task by a linear temporal logic (LTL) formula. However, some causal dependencies in complex environments may be unknown to the user in advance. Hence, when human user is specifying instructions, the robot cannot solve the tasks by simply following the given instructions. In this work, we propose a hierarchical reinforcement learning (HRL) framework in which a symbolic transition model is learned to efficiently produce high-level plans that can guide the agent efficiently solve different tasks. Specifically, the symbolic transition model is learned by inductive logic programming (ILP) to capture logic rules of state transitions. By planning over the product of the symbolic transition model and the automaton derived from the LTL formula, the agent can resolve causal dependencies and break a causally complex problem down into a sequence of simpler low-level sub-tasks. We evaluate the proposed framework on three environments in both discrete and continuous domains, showing advantages over previous representative methods.more » « less
-
Decision-making under uncertainty (DMU) is present in many important problems. An open challenge is DMU in non-stationary environments, where the dynamics of the environment can change over time. Reinforcement Learning (RL), a popular approach for DMU problems, learns a policy by interacting with a model of the environment offline. Unfortunately, if the environment changes the policy can become stale and take sub-optimal actions, and relearning the policy for the updated environment takes time and computational effort. An alternative is online planning approaches such as Monte Carlo Tree Search (MCTS), which perform their computation at decision time. Given the current environment, MCTS plans using high-fidelity models to determine promising action trajectories. These models can be updated as soon as environmental changes are detected to immediately incorporate them into decision making. However, MCTS’s convergence can be slow for domains with large state-action spaces. In this paper, we present a novel hybrid decision-making approach that combines the strengths of RL and planning while mitigating their weaknesses. Our approach, called Policy Augmented MCTS (PA-MCTS), integrates a policy’s actin-value estimates into MCTS, using the estimates to seed the action trajectories favored by the search. We hypothesize that PA-MCTS will converge more quickly than standard MCTS while making better decisions than the policy can make on its own when faced with nonstationary environments. We test our hypothesis by comparing PA-MCTS with pure MCTS and an RL agent applied to the classical CartPole environment. We find that PC-MCTS can achieve higher cumulative rewards than the policy in isolation under several environmental shifts while converging in significantly fewer iterations than pure MCTS.more » « less
-
Most social challenges fall outside of the authority of any single individual and therefore require collective action—coordinated efforts by many stakeholders to implement solutions. Despite growing interest in teaching students to lead collective action, we lack models for how to teach these skills. Collective action ostensibly involves design: the act of planning to change existing situations into preferred ones. In other domains, instructors commonly scaffold design using an instructional model known as studio critique in which students strengthen their plans by exchanging arguments with peers and instructors. This study explores whether studio critique can serve as the basis for an effective instructional model in collective action. Using design-based research methods, we designed and implemented scoping deliberations, a new instructional model that augments studio critique with domain-specific templates for planning collective action and repeats weekly to enable iterations. We used process tracing to analyze data from field notes, video, and artifacts to evaluate causal explanations for events observed in this case study. By implementing scoping deliberations in a 10-week undergraduate course, we found that this model appeared effective at scaffolding engagement in planning collective action: students articulated and refined their plans by engaging in argumentation and iteration, as expected. However, students struggled to contact the community stakeholders with whom they planned to work. As a result, their plans rested on implausible, untested assertions. These findings advance instructional science by showing that collective action may require new instructional models that help students to test their assertions against feedback from community stakeholders. Practically, scoping deliberations appear most useful for scaffolding thoughtful planning in conditions when students are already collaborating with stakeholders.more » « less
