Abstract. A typical present-day virtual actor is able to store episodes in an ad hoc manner, which does not allow for reconstructing the actor’s personal stories. This paper proposes a virtual RPG actor with a full episodic memory, which allows for this reconstruction. The paper presents the memory architecture, overviews the prototype implementation, presents a benchmark for the efficiency of the memory measurement, and details the conducted tests. 1

Abstract. Endowing an intelligent agent with an episodic memory affords it a multitude of cognitive capabilities. However, providing efficient storage and retrieval in a task-independent episodic memory presents considerable theoretical and practical challenges. We characterize the computational issues bounding an episodic memory. We explore whether even with intractable asymptotic growth, it is possible to develop efficient algorithms and data structures for episodic memory systems that are practical for real-world tasks. We present and evaluate formal and empirical results using Soar-EpMem: a task-independent integration of episodic memory with Soar 9, providing a baseline for graph-based, taskindependent episodic memory systems. 1

This paper brings together work in modeling episodic memory and reinforcement learning. We demonstrate that is possible to learn to use episodic memory retrievals while simultaneously learning to act in an external environment. In a series of three experiments we investigate learning what to retrieve from episodic memory and when to retrieve it, learning how to use temporal episodic memory retrievals, and learning how to build cues that are the conjunctions of multiple features. Our empirical results demonstrate that it is computationally feasible to learn to use episodic memory in all three experiments, and furthermore, that learning to use internal episodic memory accomplishes tasks that reinforcement learning alone does not. These experiments also expose some important interactions that arise between reinforcement learning and episodic memory.

This paper brings together work in modeling episodic memory and reinforcement learning (RL). We demonstrate that is possible to learn to use episodic memory retrievals while simultaneously learning to act in an external environment. In a series of three experiments we investigate using RL to learn what to retrieve from episodic memory and when to retrieve it, how to use temporal episodic memory retrievals, and how to build cues that are the conjunctions of multiple features. Our empirical results demonstrate that it is computationally feasible to learn to use episodic memory in the three experiments, and furthermore, that learning to use internal episodic memory accomplishes tasks that reinforcement learning alone cannot. These experiments also expose some important interactions that arise between reinforcement learning and episodic memory. In a fourth experiment, we demonstrate that an agent endowed with a simple bit memory cannot learn to use it effectively. This indicates that mechanistic characteristics of episodic memory may be essential to learning to use it, and that these characteristics are not shared by simpler memory mechanisms.

Abstract. Over their lifetimes, intelligent agents gain knowledge that may be pertinent to their decisions about acting in the world. One goal of memory system research is to develop the optimal set of encoding, storage, and retrieval mechanisms that will harness this experience to facilitate rational decisions. In this paper, we propose a direction of empirical, computational research that seeks to better understand the behavioural dynamics that arise when an agent endowed with long-term memory is situated in a task, by determining which properties of task and characteristics of memory systems are responsible for which aspects of behaviour. 1 We propose preliminary taxonomies for task and memory spaces, and also propose metrics for systematic evaluation of memory systems. 1

Abstract: In this paper we present the development of an episodic memory module for the cognitive architecture controlling an autonomous mobile simulated robot, in a simulated 3D environment. The episodic memory has the role of improving the navigation system of the robot, by evoking the objects to be considered in planning, according to episodic remembrance of earlier contacts with those objects in the past. We introduce the main background on human memory systems and episodic memory study, and provide the main ideas behind our experiment. Keywords: navigation 1.

Abstract—Recently several episodic memory models have been developed for virtual characters to increase their believability. However, none of these models addresses the issue of plausible timing of events. Here we present a model that addresses this issue. We introduce a prototype implementation and discuss the psychological underpinnings. Then we demonstrate that the model is able to mimic some psychological phenomena such as blending similar episodes. I.

Abstract not found

Available online at www.sciencedirect.com

Abstract. This work deals with the research on intelligent virtual creatures and cognitive architectures to control them. Particularly, we are interested in studying how the use of episodic memory could be useful to improve a cognitive architecture in such a task. Episodic memory is a neurocognitive mechanism for accessing past experiences that naturally makes part of human process of decision making, which usually enhances the chances of a successful behavior. Even though there are already some initiatives in such a path, we are still very far from this being a well known technology to be widely embedded in our intelligent agents. In this work we report on our ongoing efforts to bring up such technology by building up a cognitive architecture where episodic memory is a central capability. 1