Filters








1,552 Hits in 2.2 sec

Restraining Bolts for Reinforcement Learning Agents

Giuseppe De Giacomo, Luca Iocchi, Marco Favorito, Fabio Patrizi
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We have considered the case in which the agent is a reinforcement learning agent on a set of low-level (subsymbolic) features, while the restraining bolt is specified logically using linear time logic  ...  We show formally, and illustrate with examples, that, under general circumstances, the agent can learn while shaping its goals to suitably conform (as much as possible) to the restraining bolt specifications  ...  though these features are not available to the learning agent (but only to the restraining bolt).  ... 
doi:10.1609/aaai.v34i09.7114 fatcat:hv665kfvjvbhbdwjhmudzfd6ee

Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications [article]

Giuseppe De Giacomo and Luca Iocchi and Marco Favorito and Fabio Patrizi
2019 arXiv   pre-print
We consider the case in which the agent is a reinforcement learning agent on the first set of features, while the restraining bolt is specified logically using linear time logic on finite traces LTLf/LDLf  ...  We show formally, and illustrate with examples, that, under general circumstances, the agent can learn while shaping its goals to suitably conform (as much as possible) to the restraining bolt specifications  ...  First, in enforcing the restraining bolt we consider the learning agent essentially as a black box.  ... 
arXiv:1807.06333v2 fatcat:jl2rnvs7zrg25pvubjcpljwiei

Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf Restraining Specifications

Giuseppe De Giacomo, Luca Iocchi, Marco Favorito, Fabio Patrizi
2020 Zenodo  
We consider the case in which the agent is a reinforcement learning agent on the first set of features, while the restraining bolt is specified logically using linear time logic on finite traces LTLf/LDLf  ...  We show formally, and illustrate with examples, that, under general circumstances, the agent can learn while shaping its goals to suitably conform (as much as possible) to the restraining bolt specifications  ...  First, in enforcing the restraining bolt we consider the learning agent essentially as a black box.  ... 
doi:10.5281/zenodo.3944779 fatcat:jp25lvvx5ndcdi75jmdp3b7vdm

Imitation Learning over Heterogeneous Agents with Restraining Bolts

Giuseppe De Giacomo, Marco Favorito, Luca Iocchi, Fabio Patrizi
2020 Zenodo  
be incorporated into a device known as Restraining Bolt (RB).  ...  A common problem in Reinforcement Learning (RL) is that the reward function is hard to express.  ...  To deal with this, we exploit the idea of Restraining Bolt (RB) (De Giacomo et al. 2019 ): a device, with its own sensors, that can be attached to a Reinforcement Learning (RL) agent, to constrain its  ... 
doi:10.5281/zenodo.3944797 fatcat:xqzv4z7oevdr3hzsjrjuqi2ovu

IDARTS – Towards intelligent data analysis and real-time supervision for industry 4.0

Ricardo Silva Peres, Andre Dionisio Rocha, Paulo Leitao, Jose Barata
2018 Computers in industry (Print)  
supervision systems for manufacturing environments.  ...  It combines distributed data acquisition, machine learning and run-time reasoning to assist in fields such as predictive maintenance and quality control, reducing the impact of disruptive events in production  ...  of cloud-based machine learning algorithms for predictive analytics.  ... 
doi:10.1016/j.compind.2018.07.004 fatcat:7pr7sf6fsndg7l2ft327twr5oi

TERRAPIN LD.V.BUILDERS' SUPPLY CO. (HAYES) LD., TAYLOR WOODROW LD., AND SWIFTPLAN LD

1960 Reports of Patent Design and Trade Mark Cases  
Confidential information-Action to restrain misuse of information alleged to have been given in confidence by A to B for the purpose of enabling B to construct portable buildings for A-C, alleged recipients  ...  the First and Third Defendants pending trial or further order whether by themselves, their directors, servants or agents 20 or otherwise from advertising, manufacturing, offering for sale or selling or  ...  The writ was issued on the 27th 25 April and it asked for an injunction to restrain the two Defendants I have already named-and here I may say that the Second Defendants can be treated now as out of the  ... 
doi:10.1093/rpc/77.5.128 fatcat:p3xcrw6rjzb7vb4nntgaaqkozm

Damage Assessment And Repair For Older Brick Buildings

Tim D. Sass
2018 Zenodo  
For example, star bolts and decorative ironwork on the front facades of many older buildings is actually structural reinforcement needed to pull bulging brickwork back into alignment.  ...  When trying to determine the cause of damage to a brick building, the presence of star bolts or other restraining repairs indicate that the original construction may be contributing to the damage.  ... 
doi:10.5281/zenodo.1315542 fatcat:t3jcc5dtinbshmqyieubie7cp4

Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems [article]

Subbarao Kambhampati, Sarath Sreedharan, Mudit Verma, Yantian Zha, Lin Guan
2021 arXiv   pre-print
Despite the surprising power of many modern AI systems that often learn their own representations, there is significant discontent about their inscrutability and the attendant problems in their ability  ...  Symbols, like emotions, may well not be sine qua non for intelligence per se, but they will be crucial for AI systems to interact with us humans -- as we can neither turn off our emotions nor get by without  ...  ; something perhaps safely beyond scope even for a blue sky paper. the AAAI reviewers, as well as the members of the Yochan research group for helpful discussions and feedback.  ... 
arXiv:2109.09904v2 fatcat:kyzltvkulnfcrkemlncgw2anfy

The importance of learning theory and equitation science to the veterinarian

Orla Doherty, Paul D. McGreevy, Gemma Pearson
2017 Applied Animal Behaviour Science  
Advancing veterinarians" understanding of the application of learning principles for horses would improve safety, increase ease of handling and restraint during clinical procedures and increase clinical  ...  Equine veterinary practitioners" knowledge of learning theory and equitation science is minimal.  ...  Clearly, veterinarians not only have to take responsibility for their own safety but also the safety of their personnel and patients and as well as clients and their agents (McGreevy and Dixon, 2005)  ... 
doi:10.1016/j.applanim.2017.02.012 fatcat:f6bdq5gplzbz5g4dsgx72n4ht4

Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines [article]

Xuejing Zheng, Chao Yu, Chen Chen, Jianye Hao, Hankz Hankui Zhuo
2021 arXiv   pre-print
In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which enables an agent to leverage previously learned knowledge to fasten  ...  We then utilize Reward Machines (RM) to exploit structural reward functions for tasks encoded with high-level events, and propose automatic extension of RM and efficient knowledge transfer over tasks for  ...  (De Giacomo et al. 2019 ) leveraged LTL as constraints (i.e., restraining bolts) in RL. Gao et al. (Gao et al. 2019 ) used LTL to specify the unknown transition probabilities for RL.  ... 
arXiv:2111.09475v1 fatcat:jgsxwsvzbjeczf7nlew3gtfaou

Testing of Materials and Elements in Civil Engineering

Krzysztof Schabowicz
2021 Materials  
Very interesting results with significance for building practices of testing of materials and elements in civil engineering were obtained.  ...  For this reason, the articles highlighted in this issue should relate to different aspects of testing of different materials in civil engineering, from building materials and elements to building structures  ...  The method for determining the effects of restrained shrinkage is described in Standard ASTM C 1581/C 1581M-09a.  ... 
doi:10.3390/ma14123412 fatcat:gl6ogahtnjhtndyaksouthytcq

Correlated Coding of Motivation and Outcome of Decision by Dopamine Neurons

Takemasa Satoh, Sadamu Nakai, Tatsuo Sato, Minoru Kimura
2003 Journal of Neuroscience  
For instance, rate of learning could be faster when animals are motivated, whereas it could be slower when less motivated, even at identical REEs.  ...  the learning.  ...  Four head-restraining bolts and one stainless-steel recording chamber were implanted on the monkey's skulls using standard surgical procedures.  ... 
doi:10.1523/jneurosci.23-30-09913.2003 pmid:14586021 fatcat:oodf7eociffqbjafvsrahcjfr4

Dynamic characteristics of Canada's Parliament Hill towers from ambient vibrations and recorded earthquake data

Michal Kolaj, John Adams
2020 Canadian journal of civil engineering (Print)  
Both datasets found the fundamental mode to be 1.0–1.15 Hz for the Peace Tower and 2 Hz for the South-West Tower.  ...  The clock face in the Peace Tower should be connected to the masonry walls to seismically restrain it. The adequacy of the existing bolts into the masonry should be confirmed for seismic loads.  ...  In addition, the reinforcing steel in the sloped concrete roof was assumed to be 210 MPa, which is typical for reinforcing steel of that era.  ... 
doi:10.1139/cjce-2018-0474 fatcat:6bh4avs42zf7blqpj5u23f6oj4

Horse-training techniques that may defy the principles of learning theory and compromise welfare

Andrew N. McLean, Paul D. McGreevy
2010 Journal of veterinary behavior  
This review considers some contemporary training and restraining techniques that may lead to confusion or abuse in ridden and nonridden horses.  ...  The discussion also highlights an opportunity for equestrian federations to evaluate practices within the various horse sports.  ...  by negative reinforcement) that can induce the turn.  ... 
doi:10.1016/j.jveb.2010.04.002 fatcat:z4zmdy4mdfgsjpspckh6mw36le

Opinion of the Scientific Panel on Animal Health and Welfare (AHAW) on a request from the Commission related to the aspects of the biology and welfare of animals used for experimental and other scientific purposes

2005 EFSA Journal  
In a second phase, the alternative plate was reinforced and again the bees learned this, i.e. reversal learning, a type of learning considered to be advanced.  ...  Captive bolt stunning is widely used for red meat farm animals. 1.  ...  Advantages: Administration of anaesthetic agents in home cages would eliminate the need for handling animals. Mixing of unfamiliar groups of animals should be avoided.  ... 
doi:10.2903/j.efsa.2005.292 fatcat:6bhep6envzgtzlknkoszkhybbq
« Previous Showing results 1 — 15 out of 1,552 results