Massive state spaces are ubiquitous throughout planning and reinforcement learning (RL) domains: agents involved in furniture assembly, cooking automation and backgammon must grapple with problem formalisms that are much too expansive to solve by conventional tabular approaches. However, modern tabular planning and RL techniques bypass this difficulty by using propositional functions to transfer knowledge across states -- both within and across problem instances -- to solve for near optimal behaviors in very large state spaces. Here we present a means by which useful propositional functions can be inferred from observations of transition dynamics. Our approach is based upon distilling salient relational values between pairs of objects. We then use these learned propositional functions to free the RL algorithm deterministic object-oriented RMAX (DOORMAX) of its dependence on expert-provided propositional functions. We also empirically demonstrate high correspondence between these learned propositional functions and expert-provided propositional functions. Our novel DOORMAX algorithm performs at a level near that of classic DOORMAX.

Humans can ground natural language commands to tasks at both abstract and fine-grained levels of specificity. For instance, a human forklift operator can be instructed to perform a high-level action, like "grab a pallet" or a low-level action like "tilt back a little bit." While robots are also capable of grounding language commands to tasks, previous methods implicitly assume that all commands and tasks reside at a single, fixed level of abstraction. Additionally, methods that do not use multiple levels of abstraction encounter inefficient planning and execution times as they solve tasks at a single level of abstraction with large, intractable state-action spaces closely resembling real world complexity. In this work, by grounding commands to all the tasks or subtasks available in a hierarchical planning framework, we arrive at a model capable of interpreting language at multiple levels of specificity ranging from coarse to more granular. We show that the accuracy of the grounding procedure is improved when simultaneously inferring the degree of abstraction in language used to communicate the task. Leveraging hierarchy also improves efficiency: our proposed approach enables a robot to respond to a command within one second on 90% of our tasks, while baselines take over twenty seconds on half the tasks. Finally, we demonstrate that a real, physical robot can ground commands at multiple levels of abstraction allowing it to efficiently plan different subtasks within the same planning hierarchy.

Massive state spaces are ubiquitous throughout planning and reinforcement learning (RL) domains: agents involved in furniture assembly, cooking automation and backgammon must grapple with problem formalisms that are much too expansive to solve by conventional tabular approaches. However, modern tabular planning and RL techniques bypass this difficulty by using propositional functions to transfer knowledge across states — both within and across problem instances — to solve for near optimal behaviors in very large state spaces. Here we present a means by which useful propositional functions can be inferred from observations of transition dynamics. Our approach is based upon distilling salient relational values between pairs of objects. We then use these learned propositional functions to free the RL algorithm deterministic object-oriented RMAX (DOORMAX) of its dependence on expert-provided propositional functions. We also empirically demonstrate high correspondence between these learned propositional functions and expert-provided propositional functions. Our novel DOORMAX algorithm performs at a level near that of classic DOORMAX.

Performing experimental research on robotic platforms involves numerous practical complications, while studying collaborative interactions and efficiently collecting data from humans benefit from real time response. Roboticists can circumvent some complications by using simulators like Gazebo to test algorithms and building games like the Mars Escape game to collect data. Making use of existing resources for simulation and game creation requires the development of assets and algorithms along with the recruitment and training of users. We have created a Minecraft mod called BurlapCraft which enables the use of the reinforcement learning and planning library BURLAP to model and solve different tasks within Minecraft. BurlapCraft makes AI-HRI development easier in three core ways: the underlying Minecraft environment makes the construction of experiments simple for the developer and so allows the rapid prototyping of experimental setup; BURLAP contributes a wide variety of extensible algorithms for learning and planning, allowing easy iteration and development of task models and algorithms; and the familiarity and ubiquity of Minecraft trivializes the recruitment and training of users. To validate BurlapCraft as a platform for AI development, we demonstrate the execution of A*, BFS, RMax, language understanding, and learning language groundings from user demonstrations in five Minecraft "dungeons."

Probability theory as extended logic is completed such that essentially any probability may be determined. This is done by considering propositional logic (as opposed to predicate logic) as syntactically suffcient and imposing a symmetry from propositional logic. It is shown how the notions of `possibility' and `property' may be suffciently represented in propositional logic such that 1) the principle of indifference drops out and becomes essentially combinatoric in nature and 2) one may appropriately represent assumptions where one assumes there is a space of possibilities but does not assume the size of the space.

We address the problem of training an artificial agent to follow verbal commands using a set of instructions paired with demonstration traces of appropriate behavior. From this data, a mapping from instructions to tasks is learned, enabling the agent to carry out new instructions in novel environments. Our system consists of three components: semantic parsing (SP), inverse reinforcement learning (IRL), and task abstraction (TA). SP parses sentences into logical form representations, but when learning begins, the domain/task specific meanings of these representations are unknown. IRL takes demonstration traces and determines the likely reward functions that gave rise to these traces, defined over a set of provided features. TA combines results from SP and IRL over a set of training instances to create abstract goal definitions of tasks. TA also provides SP domain specific meanings for its logical forms and provides IRL the set of task-relevant features.

One criticism often advanced against abstract argumentation frameworks (AFs), is that these consider only one form of interaction between atomic arguments: specifically that an argument attacks another. Attempts to broaden the class of relationships include bipolar frameworks, where arguments support others, and abstract dialectical frameworks (ADFs). The latter, allow "acceptance'' of an argument, x, to be predicated on a given propositional function, C_x, dependent on the corresponding acceptance of its parents, i.e. those y for which occurs. Although offering a richly expressive formalism subsuming both standard and bipolar AFs, an issue that arises with ADFs is whether this expressiveness is achieved in a manner that would be infeasible within standard AFs. Can the semantics used in ADFs be mapped to some AF semantics? How many arguments are needed in an AF to "simulate'' an ADF? We show that (in a formally defined sense) any ADF can be simulated by an AF of similar size and that this translation can be realised by a polynomial time algorithm.