Author name cluster

David Aha

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

1 author row

PRL Workshop 2021 Workshop Paper

dcss ai wrapper: An API for Dungeon Crawl Stone Soup providing both Vector and Symbolic State Representations

Dustin Dannenhauer
Zohreh A. Dannenhauer
Jonathon Decker
Adam Amos-Binks
Michael Floyd
David Aha

Dungeon Crawl Stone Soup is a single-player, free, and opensource rogue-like video game with a variety of features that make it a challenge for artificial intelligence (AI) research. dcss-ai-wrapper is the first API designed to enable intelligent agents to play Dungeon Crawl Stone Soup. We describe the vector and symbolic relational state representations available through the dcss-ai-wrapper, as well as how to use the API to develop custom agents. By providing both vector and relational representations, we hope to spur advances in reinforcement learning, automated planning, and other cognitive and learning techniques. This API is similar in spirit to recent game APIs such as the Nethack Learning Environment, MALMO, ELF, and the Starcraft II API. The complexities of Dungeon Crawl Stone Soup include actions with delayed consequences, partial observability, stochastic actions where probabilities change over time, extremely sparse rewards, procedurally generated environments, sensing actions, and dynamic monsters and level-specific events. Our contributions are (1) a description of the publicly available dcssai-wrapper, (2) an API that supports both vector and PDDL representations of the DCSS game state, and (3) a high-level PDDL model of Dungeon Crawl Stone Soup compatible with the FastDownward planner. dcss-ai-wrapper is available at https: //github. com/dtdannen/dcss-ai-wrapper.

PDF Details

AAAI Conference 2018 Short Paper

Comparing Reward Shaping, Visual Hints, and Curriculum Learning

Rey Pocius
David Isele
Mark Roberts
David Aha

Common approaches to learn complex tasks in reinforcement learning include reward shaping, environmental hints, or a curriculum. Yet few studies examine how they compare to each other, when one might prefer one approach, or how they may complement each other. As a first step in this direction, we compare reward shaping, hints, and curricula for a Deep RL agent in the game of Minecraft. We seek to answer whether reward shaping, visual hints, or the curricula have the most impact on performance, which we measure as the time to reach the target, the distance from the target, the cumulative reward, or the number of actions taken. Our analyses show that performance is most impacted by the curriculum used and visual hints; shaping had less impact. For similar navigation tasks, the results suggest that designing an effective curriculum and providing appropriate hints most improve the performance. Common approaches to learn complex tasks in reinforcement learning include reward shaping, environmental hints, or a curriculum, yet few studies examine how they compare to each other. We compare these approaches for a Deep RL agent in the game of Minecraft and show performance is most impacted by the curriculum used and visual hints; shaping had less impact. For similar navigation tasks, this suggests that designing an effective curriculum with hints most improve the performance.

PDF Details

AAAI Conference 2017 Conference Paper

Incorporating Domain-Independent Planning Heuristics in Hierarchical Planning

Vikas Shivashankar
Ron Alford
David Aha

Heuristics serve as a powerful tool in modern domainindependent planning (DIP) systems by providing critical guidance during the search for high-quality solutions. However, they have not been broadly used with hierarchical planning techniques, which are more expressive and tend to scale better in complex domains by exploiting additional domainspeciﬁc knowledge. Complicating matters, we show that for Hierarchical Goal Network (HGN) planning, a goal-based hierarchical planning formalism that we focus on in this paper, any poly-time heuristic that is derived from a deleterelaxation DIP heuristic has to make some relaxation of the hierarchical semantics. To address this, we present a principled framework for incorporating DIP heuristics into HGN planning using a simple relaxation of the HGN semantics we call Hierarchy-Relaxation. This framework allows for computing heuristic estimates of HGN problems using any DIP heuristic in an admissibility-preserving manner. We demonstrate the feasibility of this approach by using the LMCut heuristic to guide an optimal HGN planner. Our empirical results with three benchmark domains demonstrate that simultaneously leveraging hierarchical knowledge and heuristic guidance substantially improves planning performance.

PDF Details

AAAI Conference 2017 Conference Paper

The AI Rebellion: Changing the Narrative

David Aha
Alexandra Coman

Sci-fi narratives permeating the collective consciousness endow AI Rebellion with ample negative connotations. However, for AI agents, as for humans, attitudes of protest, objection, and rejection have many potential benefits in support of ethics, safety, self-actualization, solidarity, and social justice, and are necessary in a wide variety of contexts. We launch a conversation on constructive AI rebellion and describe a framework meant to support discussion, implementation, and deployment of AI Rebel Agents as protagonists of positive narratives.

PDF Details

IJCAI Conference 2015 Conference Paper

Trust-Guided Behavior Adaptation Using Case-Based Reasoning

Michael Floyd
Michael Drinkwater
David Aha

The addition of a robot to a team can be difficult if the human teammates do not trust the robot. This can result in underutilization or disuse of the robot, even if the robot has skills or abilities that are necessary to achieve team goals or reduce risk. To help a robot integrate itself with a human team, we present an agent algorithm that allows a robot to estimate its trustworthiness and adapt its behavior accordingly. As behavior adaptation is performed, using case-based reasoning (CBR), information about the adaptation process is stored and used to improve the efficiency of future adaptations.

PDF Details

AAAI Conference 2014 Conference Paper

Learning Unknown Event Models

Matthew Molineaux
David Aha

Agents with incomplete environment models are likely to be surprised, and this represents an opportunity to learn. We investigate approaches for situated agents to detect surprises, discriminate among different forms of surprise, and hypothesize new models for the unknown events that surprised them. We instantiate these approaches in a new goal reasoning agent (named FOOLMETWICE), investigate its performance in simulation studies, and report that it produces plans with significantly reduced execution cost in comparison to not learning models for surprising events.

PDF Details

AAAI Conference 2010 Conference Paper

Goal-Driven Autonomy in a Navy Strategy Simulation

Matthew Molineaux
Matthew Klenk
David Aha

Modern complex games and simulations pose many challenges for an intelligent agent, including partial observability, continuous time and effects, hostile opponents, and exogenous events. We present ARTUE (Autonomous Response to Unexpected Events), a domain-independent autonomous agent that dynamically reasons about what goals to pursue in response to unexpected circumstances in these types of environments. ARTUE integrates AI research in planning, environment monitoring, explanation, goal generation, and goal management. To explain our conceptualization of the problem ARTUE addresses, we present a new conceptual framework, goal-driven autonomy, for agents that reason about their goals. We evaluate ARTUE on scenarios in the TAO Sandbox, a Navy training simulation, and demonstrate its novel architecture, which includes components for Hierarchical Task Network planning, explanation, and goal management. Our evaluation shows that ARTUE can perform well in a complex environment and that each component is necessary and contributes to the performance of the integrated system.

PDF Details

AAAI Conference 2010 Conference Paper

Planning in Dynamic Environments: Extending HTNs with Nonlinear Continuous Effects

Matthew Molineaux
Matthew Klenk
David Aha

Planning in dynamic continuous environments requires reasoning about nonlinear continuous effects, which previous Hierarchical Task Network (HTN) planners do not support. In this paper, we extend an existing HTN planner with a new state projection algorithm. To our knowledge, this is the first HTN planner that can reason about nonlinear continuous effects. We use a wait action to instruct this planner to consider continuous effects in a given state. We also introduce a new planning domain to demonstrate the benefits of planning with nonlinear continuous effects. We compare our approach with a linear continuous effects planner and a discrete effects HTN planner on a benchmark domain, which reveals that its additional costs are largely mitigated by domain knowledge. Finally, we present an initial application of this algorithm in a practical domain, a Navy training simulation, illustrating the utility of this approach for planning in dynamic continuous environments.

PDF Details