Toward Sophisticated Agent-based Universes - Statements to Introduce Some Realistic Features into Classic AI/RL Problems
نویسنده
چکیده
In this paper we analyze some common simplifications present in the traditional AI / RL problems. We argue that only facing particular conditions, often avoided in the classic statements, will allow the overcoming of the actual limits of the science, and the achievement of new advances in respect to realistic scenarios. This paper does not propose any paradigmatic revolution, but it presents a compilation of several different elements proposed more or less separately in recent AI research, unifying them by some theoretical reflections, experiments and computational solutions. Broadly, we are talking about scenarios where AI needs to deal with true situatedness agency, providing some kind of anticipatory learning mechanism to the agent in order to allow it to adapt itself to the environment.
منابع مشابه
Exploration in Feature Space for Reinforcement Learning
The infamous exploration-exploitation dilemma is one of the oldest and most important problems in reinforcement learning (RL). Deliberate and effective exploration is necessary for RL agents to succeed in most environments. However, until very recently even very sophisticated RL algorithms employed simple, undirected exploration strategies in large-scale RL tasks. We introduce a new optimistic ...
متن کاملIntegrating Case-Based Reasoning with Reinforcement Learning for Real-Time Strategy Game Micromanagement
This paper describes the conception of a hybrid Reinforcement Learning (RL) and Case-Based Reasoning (CBR) approach to managing combat units in strategy games. Both methods are combined into an AI agent that is evaluated by using the real-time strategy (RTS) computer game StarCraft as a test bed. The eventual aim of this approach is an AI agent that has the same actions and information at its d...
متن کاملArgumentation accelerated reinforcement learning
Reinforcement Learning (RL) is a popular statistical Artificial Intelligence (AI) technique for building autonomous agents, but it suffers from the curse of dimensionality: the computational requirement for obtaining the optimal policies grows exponentially with the size of the state space. Integrating heuristics into RL has proven to be an effective approach to combat this curse, but deriving ...
متن کاملAgent Theory: Autonomy and Self-Control
AI seems to be developing toward a theory of intelligent agents (IA), however, the theoretical basis which should underly the notion of agency has remained strikingly underdeveloped. This paper is intended to improve on this situation, by analysing the most basic notions necessary for a theory of agency: action, self, control, autonomy and adaptivity. Our main thesis is that autonomy is the ess...
متن کاملThe Reinforcement Learning Competition 2014
R einforcement learning (RL) is the problem of learning how to act only from interaction and limited reinforcement. An agent takes actions in an unknown environment , observes their effects, and obtains rewards. The agent's aim is to learn how the environment works in order to maximize the total reward obtained during its lifetime. RL problems are quite general. They can subsume almost any arti...
متن کامل