Search results for "reinforcement learning"
showing 10 items of 95 documents
Calibrating a Motion Model Based on Reinforcement Learning for Pedestrian Simulation
2012
In this paper, the calibration of a framework based in Multi-agent Reinforcement Learning (RL) for generating motion simulations of pedestrian groups is presented. The framework sets a group of autonomous embodied agents that learn to control individually its instant velocity vector in scenarios with collisions and friction forces. The result of the process is a different learned motion controller for each agent. The calibration of both, the physical properties involved in the motion of our embodied agents and the corresponding dynamics, is an important issue for a realistic simulation. The physics engine used has been calibrated with values taken from real pedestrian dynamics. Two experime…
Multi-agent Reinforcement Learning for Simulating Pedestrian Navigation
2012
In this paper we introduce a Multi-agent system that uses Reinforcement Learning (RL) techniques to learn local navigational behaviors to simulate virtual pedestrian groups. The aim of the paper is to study empirically the validity of RL to learn agent-based navigation controllers and their transfer capabilities when they are used in simulation environments with a higher number of agents than in the learned scenario. Two RL algorithms which use Vector Quantization (VQ) as the generalization method for the space state are presented. Both strategies are focused on obtaining a good vector quantizier that generalizes adequately the state space of the agents. We empirically state the convergence…
A generic model of reinforcement learning combined with macroscopic cellular automata to simulate land use change
2019
Better understanding the evolution of land cover is a priority concern in the field of land use change study. This evolution can be the result of interactions between major factors. The study of land use change is included in territorial planning to inform planners and policy makers of possible developments they will face. Land use models are useful for reasonable land use management to optimize future land management decisions. In this paper we present an original theoretical model of reinforcement learning combined with macroscopic cellular automata to simulate land use change.
Using the Theory of Regular Functions to Formally Prove the ε-Optimality of Discretized Pursuit Learning Algorithms
2014
Learning Automata LA can be reckoned to be the founding algorithms on which the field of Reinforcement Learning has been built. Among the families of LA, Estimator Algorithms EAs are certainly the fastest, and of these, the family of Pursuit Algorithms PAs are the pioneering work. It has recently been reported that the previous proofs for e-optimality for all the reported algorithms in the family of PAs have been flawed. We applaud the researchers who discovered this flaw, and who further proceeded to rectify the proof for the Continuous Pursuit Algorithm CPA. The latter proof, though requires the learning parameter to be continuously changing, is, to the best of our knowledge, the current …
Exception-Tolerant Hierarchical Knowledge Bases for Forward Model Learning
2021
This article provides an overview of the recently proposed forward model approximation framework for learning games of the general video game artificial intelligence (GVGAI) framework. In contrast to other general game-playing algorithms, the proposed agent model does not need a full description of the game but can learn the game's rules by observing game state transitions. Based on hierarchical knowledge bases, the forward model can be learned and revised during game-play, improving the accuracy of the agent's state predictions over time. This allows the application of simulation-based search algorithms and belief revision techniques to previously unknown settings. We show that the propose…
Realizing Undelayed N-step TD prediction with neural networks
2010
There exist various techniques to extend reinforcement learning algorithms, e.g., eligibility traces and planning. In this paper, an approach is proposed, which combines several extension techniques, such as using eligibility-like traces, using approximators as value functions and exploiting the model of the environment. The obtained method, ‘Undelayed n-step TD prediction’ (TD-P), has produced competitive results when put in conditions of not fully observable environment.
Learning competitive pricing strategies by multi-agent reinforcement learning
2003
Abstract In electronic marketplaces automated and dynamic pricing is becoming increasingly popular. Agents that perform this task can improve themselves by learning from past observations, possibly using reinforcement learning techniques. Co-learning of several adaptive agents against each other may lead to unforeseen results and increasingly dynamic behavior of the market. In this article we shed some light on price developments arising from a simple price adaptation strategy. Furthermore, we examine several adaptive pricing strategies and their learning behavior in a co-learning scenario with different levels of competition. Q-learning manages to learn best-reply strategies well, but is e…
MARL-Ped: A multi-agent reinforcement learning based framework to simulate pedestrian groups
2014
Abstract Pedestrian simulation is complex because there are different levels of behavior modeling. At the lowest level, local interactions between agents occur; at the middle level, strategic and tactical behaviors appear like overtakings or route choices; and at the highest level path-planning is necessary. The agent-based pedestrian simulators either focus on a specific level (mainly in the lower one) or define strategies like the layered architectures to independently manage the different behavioral levels. In our Multi-Agent Reinforcement-Learning-based Pedestrian simulation framework (MARL-Ped) the situation is addressed as a whole. Each embodied agent uses a model-free Reinforcement L…
Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models
2017
This paper analyzes the emergent behaviors of pedestrian groups that learn through the multiagent reinforcement learning model developed in our group. Five scenarios studied in the pedestrian model literature, and with different levels of complexity, were simulated in order to analyze the robustness and the scalability of the model. Firstly, a reduced group of agents must learn by interaction with the environment in each scenario. In this phase, each agent learns its own kinematic controller, that will drive it at a simulation time. Secondly, the number of simulated agents is increased, in each scenario where agents have previously learnt, to test the appearance of emergent macroscopic beha…
A multi-agent system reinforcement learning based optimal power flow for islanded microgrids
2016
In this paper, a distributed intelligence algorithm is used to manage the optimal power flow problem in islanded microgrids. The methodology provides a suboptimal solution although the error is limited to a few percent as compared to a centralized approach. The solution algorithm is multi-agent based. According to the method, couples of agents communicate with each other only if the buses where they are located are electrically connected. The overall prizing system required for learning uses a feedback from an approximated model of the network. Based on the latter, a distributed reiforcement learning algorithm is implemented to minimize the joule losses while meeting operational constraints…