Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction
We introduce a data-driven, model-agnostic technique for generating a human-interpretable summary of the salient points of contrast within an evolving dynamical system, such as the learning process of a control agent. It involves the aggregation of transition data along both spatial and temporal dimensions according to an information-theoretic divergence measure. A practical algorithm is outlined for continuous state spaces, and deployed to summarise the learning histories of deep reinforcement learning agents with the aid of graphical and textual communication methods. We expect our method to be complementary to existing techniques in the realm of agent interpretability.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Towards Contrastive Explanations for Comparing the Ethics of Plans
The development of robotics and AI agents has enabled their wider usage in human surroundings. AI agents are more trusted to make increasingly important decisions with potentially critical outcomes. It is essential to co…
EthicsReach-Avoid-Stay-Collision-Avoidance Negotiation Framework for Multi-Agent Systems via Spatiotemporal Tubes
This study presents a multi-agent negotiation-based framework to obtain collision-free paths while performing prescribed-time reach-avoid-stay (RAS) tasks for agents with unknown dynamics and bounded disturbance. By empl…
Collision AvoidanceDrone navigationRobot NavigationPredictive Information Accelerates Learning in RL
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the predictive information is useful in RL, since the ability to model what will ha…
continuous-controlContinuous ControlMulti-axis Attentive Prediction for Sparse EventData: An Application to Crime Prediction
Spatiotemporal prediction of event data is a challenging task with a long history of research. While recent work in spatiotemporal prediction has leveraged deep sequential models that substantially improve over classical…
Contrastive LearningCrime PredictionPredictionFine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning
As the most essential property in a video, motion information is critical to a robust and generalized video representation. To inject motion dynamics, recent works have adopted frame difference as the source of motion in…
Contrastive LearningDecoderDiversityRepresentation Learning