Model-Based and Model-Free Social Cognition

2019 ◽  
Author(s):  
Leor M Hackel ◽  
Jeffrey Jordan Berg ◽  
Björn Lindström ◽  
David Amodio
Keyword(s):  
Reinforcement Learning ◽  
Social Cognition ◽  
Learning Strategies ◽  
Memory Systems ◽  
Learning Task ◽  
Financial Advisors ◽  
Model Based ◽  
Model Free ◽  
Systems Model ◽  
Task Assessment

Do habits play a role in our social impressions? To investigate the contribution of habits to the formation of social attitudes, we examined the roles of model-free and model-based reinforcement learning in social interactions—computations linked in past work to habit and planning, respectively. Participants in this study learned about novel individuals in a sequential reinforcement learning paradigm, choosing financial advisors who led them to high- or low-paying stocks. Results indicated that participants relied on both model-based and model-free learning, such that each independently predicted choice during the learning task and self-reported liking in a post-task assessment. Specifically, participants liked advisors who could provide large future rewards as well as advisors who had provided them with large rewards in the past. Moreover, participants varied in their use of model-based and model-free learning strategies, and this individual difference influenced the way in which learning related to self-reported attitudes: among participants who relied more on model-free learning, model-free social learning related more to post-task attitudes. We discuss implications for attitudes, trait impressions, and social behavior, as well as the role of habits in a memory systems model of social cognition.

scholarly journals The comparable strategic flexibility of model-free and model-based learning

2020 ◽  
Author(s):  
Alexandre L. S. Filipowicz ◽  
Jonathan Levine ◽  
Eugenio Piasini ◽  
Gaia Tavoni ◽  
Joseph W. Kable ◽  
...  
Keyword(s):  
Computational Complexity ◽  
Learning Strategies ◽  
Response Times ◽  
Human Subjects ◽  
Learning Task ◽  
Strategic Flexibility ◽  
Information Complexity ◽  
Model Based ◽  
Model Free ◽  
Processing Resources

AbstractDifferent learning strategies are thought to fall along a continuum that ranges from simple, inflexible, and fast “model-free” strategies, to more complex, flexible, and deliberative “model-based strategies”. Here we show that, contrary to this proposal, strategies at both ends of this continuum can be equally flexible, effective, and time-intensive. We analyzed behavior of adult human subjects performing a canonical learning task used to distinguish between model-free and model-based strategies. Subjects using either strategy showed similarly high information complexity, a measure of strategic flexibility, and comparable accuracy and response times. This similarity was apparent despite the generally higher computational complexity of model-based algorithms and fundamental differences in how each strategy learned: model-free learning was driven primarily by observed past responses, whereas model-based learning was driven primarily by inferences about latent task features. Thus, model-free and model-based learning differ in the information they use to learn but can support comparably flexible behavior.Statement of RelevanceThe distinction between model-free and model-based learning is an influential framework that has been used extensively to understand individual- and task-dependent differences in learning by both healthy and clinical populations. A common interpretation of this distinction that model-based strategies are more complex and therefore more flexible than model-free strategies. However, this interpretation conflates computational complexity, which relates to processing resources and generally higher for model-based algorithms, with information complexity, which reflects flexibility but has rarely been measured. Here we use a metric of information complexity to demonstrate that, contrary to this interpretation, model-free and model-based strategies can be equally flexible, effective, and time-intensive and are better distinguished by the nature of the information from which they learn. Our results counter common interpretations of model-free versus model-based learning and demonstrate the general usefulness of information complexity for assessing different forms of strategic flexibility.

scholarly journals Episodic Control as Meta-Reinforcement Learning

2018 ◽  
Author(s):  
S Ritter ◽  
JX Wang ◽  
Z Kurth-Nelson ◽  
M Botvinick
Keyword(s):  
Reinforcement Learning ◽  
Episodic Memory ◽  
Learning Strategies ◽  
Learning Algorithms ◽  
Memory System ◽  
Generic Model ◽  
Model Based ◽  
Model Free

AbstractRecent research has placed episodic reinforcement learning (RL) alongside model-free and model-based RL on the list of processes centrally involved in human reward-based learning. In the present work, we extend the unified account of model-free and model-based RL developed by Wang et al. (2018) to further integrate episodic learning. In this account, a generic model-free “meta-learner” learns to deploy and coordinate among all of these learning algorithms. The meta-learner learns through brief encounters with many novel tasks, so that it learns to learn about new tasks. We show that when equipped with an episodic memory system inspired by theories of reinstatement and gating, the meta-learner learns to use the episodic and model-based learning algorithms observed in humans in a task designed to dissociate among the influences of various learning strategies. We discuss implications and predictions of the model.

scholarly journals Simple Plans or Sophisticated Habits? State, Transition and Learning Interactions in the Two-step Task.

2015 ◽  
Author(s):  
Thomas Akam ◽  
Rui Costa ◽  
Peter Dayan
Keyword(s):  
Reinforcement Learning ◽  
Learning Strategies ◽  
Animal Studies ◽  
State Transition ◽  
Model Based ◽  
Model Free ◽  
Extended Training ◽  
Subsequent Trial ◽  
Decision Variables ◽  
Analysis Strategy

The recently developed ‘two-step’ behavioural task promises to differentiate model-based or goal-directed from model-free or habitual reinforcement learning, while generating neurophysiologically-friendly decision datasets with parametric variation of decision variables. These desirable features have prompted widespread adoption of the task. However, the signatures of model-based control can be elusive – here, we investigate model-free learning methods that, depending on the analysis strategy, can masquerade as being model-based. We first show that unadorned model-free reinforcement learning can induce correlations between action values at the start of the trial and the subsequent trial events in such a way that analysis based on comparing successive trials can lead to erroneous conclusions. We also suggest a correction to the analysis that can alleviate this problem. We then consider model-free reinforcement learning strategies based on different state representations from those envisioned by the experimenter, which generate behaviour that appears model-based under these, and also more sophisticated, analyses. The existence of such strategies is of particular relevance to the design and interpretation of animal studies using the two-step task, as extended training and a sharp contrast between good and bad options are likely to promote their use.

Proximal policy optimization with model-based methods

2022 ◽  
pp. 1-12
Author(s):  
Shuailong Li ◽  
Wei Zhang ◽  
Huiwen Zhang ◽  
Xin Zhang ◽  
Yuquan Leng
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Transition Model ◽  
Practical Applications ◽  
Original Algorithm ◽  
Policy Performance ◽  
Model Based ◽  
Model Free ◽  
Future State ◽  
Policy Optimization

Model-free reinforcement learning methods have successfully been applied to practical applications such as decision-making problems in Atari games. However, these methods have inherent shortcomings, such as a high variance and low sample efficiency. To improve the policy performance and sample efficiency of model-free reinforcement learning, we propose proximal policy optimization with model-based methods (PPOMM), a fusion method of both model-based and model-free reinforcement learning. PPOMM not only considers the information of past experience but also the prediction information of the future state. PPOMM adds the information of the next state to the objective function of the proximal policy optimization (PPO) algorithm through a model-based method. This method uses two components to optimize the policy: the error of PPO and the error of model-based reinforcement learning. We use the latter to optimize a latent transition model and predict the information of the next state. For most games, this method outperforms the state-of-the-art PPO algorithm when we evaluate across 49 Atari games in the Arcade Learning Environment (ALE). The experimental results show that PPOMM performs better or the same as the original algorithm in 33 games.

scholarly journals Hybrid-Model-Based Deep Reinforcement Learning for Heating, Ventilation, and Air-Conditioning Control

2021 ◽  
Vol 8 ◽  
Author(s):  
Huan Zhao ◽  
Junhua Zhao ◽  
Ting Shu ◽  
Zibin Pan
Keyword(s):  
Reinforcement Learning ◽  
Energy Consumption ◽  
Hybrid Model ◽  
Learning Process ◽  
Energy Cost ◽  
Air Conditioning ◽  
Electricity Price ◽  
Learning Efficiency ◽  
Model Based ◽  
Model Free

Buildings account for a large proportion of the total energy consumption in many countries and almost half of the energy consumption is caused by the Heating, Ventilation, and air-conditioning (HVAC) systems. The model predictive control of HVAC is a complex task due to the dynamic property of the system and environment, such as temperature and electricity price. Deep reinforcement learning (DRL) is a model-free method that utilizes the “trial and error” mechanism to learn the optimal policy. However, the learning efficiency and learning cost are the main obstacles of the DRL method to practice. To overcome this problem, the hybrid-model-based DRL method is proposed for the HVAC control problem. Firstly, a specific MDPs is defined by considering the energy cost, temperature violation, and action violation. Then the hybrid-model-based DRL method is proposed, which utilizes both the knowledge-driven model and the data-driven model during the whole learning process. Finally, the protection mechanism and adjusting reward methods are used to further reduce the learning cost. The proposed method is tested in a simulation environment using the Australian Energy Market Operator (AEMO) electricity price data and New South Wales temperature data. Simulation results show that 1) the DRL method can reduce the energy cost while maintaining the temperature satisfactory compared to the short term MPC method; 2) the proposed method improves the learning efficiency and reduces the learning cost during the learning process compared to the model-free method.

Sign in / Sign up

Export Citation Format

Share Document