paper-with-me

홈 › Papers

Lights out: training RL agents robust to temporary blindness

2023-12-05 · N. Ordonez, M. Tromp, P. M. Julbe, W. Böhmer

Agents trained with DQN rely on an observation at each timestep to decide what action to take next. However, in real world applications observations can change or be missing entirely. Examples of this could be a light bulb breaking down, or the wallpaper in a certain room changing. While these situations change the actual observation, the underlying optimal policy does not change. Because of this we want our agent to continue taking actions until it receives a (recognized) observation again. To achieve this we introduce a combination of a neural network architecture that uses hidden representations of the observations and a novel n-step loss function. Our implementation is able to withstand location based blindness stretches longer than the ones it was trained on, and therefore shows robustness to temporary blindness. For access to our implementation, please email Nathan, Marije, or Pau.

📄 PDF Abstract BibTeX arXiv:2312.02665

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

Interpretive Blindness

2021-10-19 · Nicholas Asher, Julie Hunter

We model here an epistemic bias we call \textit{interpretive blindness} (IB). IB is a special problem for learning from testimony, in which one acquires information only from text or conversation. We show that IB follows…

An Eye on Clinical BERT: Investigating Language Model Generalization for Diabetic Eye Disease Phenotyping

2023-11-15 · Keith Harrigian, Tina Tang, Anthony Gonzales, Cindy X. Cai 외

Diabetic eye disease is a major cause of blindness worldwide. The ability to monitor relevant clinical trajectories and detect lapses in care is critical to managing the disease and preventing blindness. Alas, much of th…

Language ModelingLanguage Modelling

Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception

2025-10-27 · Yize Cheng, Arshia Soltani Moakhar, Chenrui Fan, Parsa Hosseini 외 arxiv

Large language model (LLM) agents are increasingly used to interact with and execute tasks in dynamic environments. However, a critical yet overlooked limitation of these agents is that they, by default, assume a station…

Beyond single-channel agentic benchmarking

2026-02-05 · Nelu D. Radpour arxiv

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single…

Early Blindness Detection Based on Retinal Images Using Ensemble Learning

2020-06-12 · Niloy Sikder, Md. Sanaullah Chowdhury, Abu Shamim Mohammad Arif, Abdullah-Al Nahid

Diabetic retinopathy (DR) is the primary cause of vision loss among grownup people around the world. In four out of five cases having diabetes for a prolonged period leads to DR. If detected early, more than 90 percent o…

Ensemble Learning