Zobrazeno 1 - 10
of 595
pro vyhledávání: '"Balloch, A."'
Interpretability of deep reinforcement learning systems could assist operators with understanding how they interact with their environment. Vector quantization methods -- also called codebook methods -- discretize a neural network's latent space that
Externí odkaz:
http://arxiv.org/abs/2407.19532
Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks with learnin
Externí odkaz:
http://arxiv.org/abs/2407.00264
Autor:
Balloch, Jonathan C., Bhagat, Rishav, Zollicoffer, Geigh, Jia, Ruoran, Kim, Julia, Riedl, Mark O.
In deep reinforcement learning (RL) research, there has been a concerted effort to design more efficient and productive exploration methods while solving sparse-reward problems. These exploration methods often share common principles (e.g., improving
Externí odkaz:
http://arxiv.org/abs/2404.02235
Autor:
Zollicoffer, Geigh, Eaton, Kenneth, Balloch, Jonathan, Kim, Julia, Riedl, Mark O., Wright, Robert
Reinforcement learning (RL) using world models has found significant recent successes. However, when a sudden change to world mechanics or properties occurs then agent performance and reliability can dramatically decline. We refer to the sudden chang
Externí odkaz:
http://arxiv.org/abs/2310.08731
Autor:
Balloch, Jonathan, Lin, Zhiyu, Wright, Robert, Peng, Xiangyu, Hussain, Mustafa, Srinivas, Aarun, Kim, Julia, Riedl, Mark O.
Open-world novelty--a sudden change in the mechanics or properties of an environment--is a common occurrence in the real world. Novelty adaptation is an agent's ability to improve its policy performance post-novelty. Most reinforcement learning (RL)
Externí odkaz:
http://arxiv.org/abs/2301.06294
Autor:
Jasmine Balloch, Shankar Sridharan, Geralyn Oldham, Jo Wray, Paul Gough, Robert Robinson, Neil J. Sebire, Saleh Khalil, Elham Asgari, Christopher Tan, Andrew Taylor, Dominic Pimenta
Publikováno v:
Future Healthcare Journal, Vol 11, Iss 3, Pp 100157- (2024)
Background: Electronic health records (EHRs) have contributed to increased workloads for clinicians. Ambient artificial intelligence (AI) tools offer potential solutions, aiming to streamline clinical documentation and alleviate cognitive strain on h
Externí odkaz:
https://doaj.org/article/9a7efb15e4e5465caa8600a1382cc7b2
The exploration--exploitation trade-off in reinforcement learning (RL) is a well-known and much-studied problem that balances greedy action selection with novel experience, and the study of exploration methods is usually only considered in the contex
Externí odkaz:
http://arxiv.org/abs/2210.06168
Autor:
Balloch, Jonathan, Lin, Zhiyu, Hussain, Mustafa, Srinivas, Aarun, Wright, Robert, Peng, Xiangyu, Kim, Julia, Riedl, Mark
A robust body of reinforcement learning techniques have been developed to solve complex sequential decision making problems. However, these methods assume that train and evaluation tasks come from similarly or identically distributed environments. Th
Externí odkaz:
http://arxiv.org/abs/2203.12117
Autor:
Balloch, Jasmine, Sridharan, Shankar, Oldham, Geralyn, Wray, Jo, Gough, Paul, Robinson, Robert, Sebire, Neil J., Khalil, Saleh, Asgari, Elham, Tan, Christopher, Taylor, Andrew, Pimenta, Dominic
Publikováno v:
In Future Healthcare Journal September 2024 11(3)
Neural language model-based approaches to automated story generation suffer from two important limitations. First, language model-based story generators generally do not work toward a given goal or ending. Second, they often lose coherence as the sto
Externí odkaz:
http://arxiv.org/abs/2112.03808