Limits...
Which is the best intrinsic motivation signal for learning multiple skills?

Santucci VG, Baldassarre G, Mirolli M - Front Neurorobot (2013)

Bottom Line: We tested the system in a setup with continuous states and actions, in particular, with a kinematic robotic arm that has to learn different reaching tasks.We compare the results of different versions of the system driven by several different intrinsic motivation signals.The results show (a) that intrinsic reinforcements purely based on the knowledge of the system are not appropriate to guide the acquisition of multiple skills, and (b) that the stronger the link between the IM signal and the competence of the system, the better the performance.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Computational Embodied Neuroscience, Isituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche Roma, Italy ; School of Computing and Mathematics, University of Plymouth Plymouth, UK.

ABSTRACT
Humans and other biological agents are able to autonomously learn and cache different skills in the absence of any biological pressure or any assigned task. In this respect, Intrinsic Motivations (i.e., motivations not connected to reward-related stimuli) play a cardinal role in animal learning, and can be considered as a fundamental tool for developing more autonomous and more adaptive artificial agents. In this work, we provide an exhaustive analysis of a scarcely investigated problem: which kind of IM reinforcement signal is the most suitable for driving the acquisition of multiple skills in the shortest time? To this purpose we implemented an artificial agent with a hierarchical architecture that allows to learn and cache different skills. We tested the system in a setup with continuous states and actions, in particular, with a kinematic robotic arm that has to learn different reaching tasks. We compare the results of different versions of the system driven by several different intrinsic motivation signals. The results show (a) that intrinsic reinforcements purely based on the knowledge of the system are not appropriate to guide the acquisition of multiple skills, and (b) that the stronger the link between the IM signal and the competence of the system, the better the performance.

No MeSH data available.


Related in: MedlinePlus

Scheme of the different experimental conditions, divided by typology of signal, typology of intrinsic motivations, input, and training algorithm. Note that the random (RND) condition is not mentioned in this table because it does not use any reinforcement signal to determine the selection of the experts. See Section 2.3.1 and 2.3.2 for a detailed description of all the different conditions.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3824099&req=5

Figure 3: Scheme of the different experimental conditions, divided by typology of signal, typology of intrinsic motivations, input, and training algorithm. Note that the random (RND) condition is not mentioned in this table because it does not use any reinforcement signal to determine the selection of the experts. See Section 2.3.1 and 2.3.2 for a detailed description of all the different conditions.

Mentions: As mentioned in section 1, we tested the IM signals and the mechanisms (predictors) implemented to generate such signals that are most used in the literature on IMs (see Figure 3 for a scheme of the different experimental conditions).


Which is the best intrinsic motivation signal for learning multiple skills?

Santucci VG, Baldassarre G, Mirolli M - Front Neurorobot (2013)

Scheme of the different experimental conditions, divided by typology of signal, typology of intrinsic motivations, input, and training algorithm. Note that the random (RND) condition is not mentioned in this table because it does not use any reinforcement signal to determine the selection of the experts. See Section 2.3.1 and 2.3.2 for a detailed description of all the different conditions.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3824099&req=5

Figure 3: Scheme of the different experimental conditions, divided by typology of signal, typology of intrinsic motivations, input, and training algorithm. Note that the random (RND) condition is not mentioned in this table because it does not use any reinforcement signal to determine the selection of the experts. See Section 2.3.1 and 2.3.2 for a detailed description of all the different conditions.
Mentions: As mentioned in section 1, we tested the IM signals and the mechanisms (predictors) implemented to generate such signals that are most used in the literature on IMs (see Figure 3 for a scheme of the different experimental conditions).

Bottom Line: We tested the system in a setup with continuous states and actions, in particular, with a kinematic robotic arm that has to learn different reaching tasks.We compare the results of different versions of the system driven by several different intrinsic motivation signals.The results show (a) that intrinsic reinforcements purely based on the knowledge of the system are not appropriate to guide the acquisition of multiple skills, and (b) that the stronger the link between the IM signal and the competence of the system, the better the performance.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Computational Embodied Neuroscience, Isituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche Roma, Italy ; School of Computing and Mathematics, University of Plymouth Plymouth, UK.

ABSTRACT
Humans and other biological agents are able to autonomously learn and cache different skills in the absence of any biological pressure or any assigned task. In this respect, Intrinsic Motivations (i.e., motivations not connected to reward-related stimuli) play a cardinal role in animal learning, and can be considered as a fundamental tool for developing more autonomous and more adaptive artificial agents. In this work, we provide an exhaustive analysis of a scarcely investigated problem: which kind of IM reinforcement signal is the most suitable for driving the acquisition of multiple skills in the shortest time? To this purpose we implemented an artificial agent with a hierarchical architecture that allows to learn and cache different skills. We tested the system in a setup with continuous states and actions, in particular, with a kinematic robotic arm that has to learn different reaching tasks. We compare the results of different versions of the system driven by several different intrinsic motivation signals. The results show (a) that intrinsic reinforcements purely based on the knowledge of the system are not appropriate to guide the acquisition of multiple skills, and (b) that the stronger the link between the IM signal and the competence of the system, the better the performance.

No MeSH data available.


Related in: MedlinePlus