Shaping Model-Free Reinforcement-Learning with Model-Based Pseudorewards

2018 ◽  
Author(s):  
Paul Krueger ◽  
Thomas Griffiths
Keyword(s):  
Reinforcement Learning ◽  
Model Based ◽  
Model Free

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.

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.

scholarly journals Severe Sexual Abuse Reduces Frontoparietal Network Activity during Model-Based Reinforcement Learning Updates

2019 ◽  
Author(s):  
Allison Letkiewicz ◽  
Amy L. Cochran ◽  
Josh M. Cisler
Keyword(s):  
Sexual Abuse ◽  
Reinforcement Learning ◽  
Learning Styles ◽  
Computational Models ◽  
Learning Strategy ◽  
Network Activity ◽  
Model Based ◽  
Model Free ◽  
Frontoparietal Network ◽  
Assaultive Trauma

Trauma and trauma-related disorders are characterized by altered learning styles. Two learning processes that have been delineated using computational modeling are model-free and model-based reinforcement learning (RL), characterized by trial and error and goal-driven, rule-based learning, respectively. Prior research suggests that model-free RL is disrupted among individuals with a history of assaultive trauma and may contribute to altered fear responding. Currently, it is unclear whether model-based RL, which involves building abstract and nuanced representations of stimulus-outcome relationships to prospectively predict action-related outcomes, is also impaired among individuals who have experienced trauma. The present study sought to test the hypothesis of impaired model-based RL among adolescent females exposed to assaultive trauma. Participants (n=60) completed a three-arm bandit RL task during fMRI acquisition. Two computational models compared the degree to which each participant’s task behavior fit the use of a model-free versus model-based RL strategy. Overall, a greater portion of participants’ behavior was better captured by the model-based than model-free RL model. Although assaultive trauma did not predict learning strategy use, greater sexual abuse severity predicted less use of model-based compared to model-free RL. Additionally, severe sexual abuse predicted less left frontoparietal network encoding of model-based RL updates, which was not accounted for by PTSD. Given the significant impact that sexual trauma has on mental health and other aspects of functioning, it is plausible that altered model-based RL is an important route through which clinical impairment emerges.

scholarly journals Prefrontal solution to the bias-variance tradeoff during reinforcement learning

2020 ◽  
Author(s):  
Dongjae Kim ◽  
Jaeseung Jeong ◽  
Sang Wan Lee
Keyword(s):  
Adaptive Control ◽  
Reinforcement Learning ◽  
Prediction Error ◽  
Brain Regions ◽  
Decision Task ◽  
Prediction Errors ◽  
Model Based ◽  
Model Free ◽  
Bias Variance ◽  
The Brain

AbstractThe goal of learning is to maximize future rewards by minimizing prediction errors. Evidence have shown that the brain achieves this by combining model-based and model-free learning. However, the prediction error minimization is challenged by a bias-variance tradeoff, which imposes constraints on each strategy’s performance. We provide new theoretical insight into how this tradeoff can be resolved through the adaptive control of model-based and model-free learning. The theory predicts the baseline correction for prediction error reduces the lower bound of the bias–variance error by factoring out irreducible noise. Using a Markov decision task with context changes, we showed behavioral evidence of adaptive control. Model-based behavioral analyses show that the prediction error baseline signals context changes to improve adaptability. Critically, the neural results support this view, demonstrating multiplexed representations of prediction error baseline within the ventrolateral and ventromedial prefrontal cortex, key brain regions known to guide model-based and model-free learning.One sentence summaryA theoretical, behavioral, computational, and neural account of how the brain resolves the bias-variance tradeoff during reinforcement learning is described.

Model-Based Multi-Objective Reinforcement Learning by a Reward Occurrence Probability Vector

2020 ◽  
pp. 269-295
Author(s):  
Tomohiro Yamaguchi ◽  
Shota Nagahama ◽  
Yoshihiro Ichikawa ◽  
Yoshimichi Honma ◽  
Keiki Takadama
Keyword(s):  
Reinforcement Learning ◽  
Experimental Results ◽  
Previous Model ◽  
Pareto Optimal ◽  
Occurrence Probability ◽  
Contrast Model ◽  
Multi Objective ◽  
Model Based ◽  
Model Free ◽  
Optimal Policies

This chapter describes solving multi-objective reinforcement learning (MORL) problems where there are multiple conflicting objectives with unknown weights. Previous model-free MORL methods take large number of calculations to collect a Pareto optimal set for each V/Q-value vector. In contrast, model-based MORL can reduce such a calculation cost than model-free MORLs. However, previous model-based MORL method is for only deterministic environments. To solve them, this chapter proposes a novel model-based MORL method by a reward occurrence probability (ROP) vector with unknown weights. The experimental results are reported under the stochastic learning environments with up to 10 states, 3 actions, and 3 reward rules. The experimental results show that the proposed method collects all Pareto optimal policies, and it took about 214 seconds (10 states, 3 actions, 3 rewards) for total learning time. In future research directions, the ways to speed up methods and how to use non-optimal policies are discussed.

scholarly journals Don't Think, Just Feel the Music: Individuals with Strong Pavlovian-to-Instrumental Transfer Effects Rely Less on Model-based Reinforcement Learning

2016 ◽  
Vol 28 (7) ◽  
pp. 985-995 ◽  
Author(s):  
Miriam Sebold ◽  
Daniel J. Schad ◽  
Stephan Nebe ◽  
Maria Garbusow ◽  
Elisabeth Jünger ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Individual Variation ◽  
The Other ◽  
Transfer Effects ◽  
Behavioral Choice ◽  
Model Based ◽  
Model Free ◽  
Underlying Substrate

Behavioral choice can be characterized along two axes. One axis distinguishes reflexive, model-free systems that slowly accumulate values through experience and a model-based system that uses knowledge to reason prospectively. The second axis distinguishes Pavlovian valuation of stimuli from instrumental valuation of actions or stimulus–action pairs. This results in four values and many possible interactions between them, with important consequences for accounts of individual variation. We here explored whether individual variation along one axis was related to individual variation along the other. Specifically, we asked whether individuals' balance between model-based and model-free learning was related to their tendency to show Pavlovian interferences with instrumental decisions. In two independent samples with a total of 243 participants, Pavlovian–instrumental transfer effects were negatively correlated with the strength of model-based reasoning in a two-step task. This suggests a potential common underlying substrate predisposing individuals to both have strong Pavlovian interference and be less model-based and provides a framework within which to interpret the observation of both effects in addiction.

Sign in / Sign up

Export Citation Format

Share Document