Search for: All records

Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features. To mitigate this prob- lem, we propose learning Task Informed Ab- stractions (TIA) that explicitly separates reward- correlated visual features from distractors. For learning TIA, we introduce the formalism of Task Informed MDP (TiMDP) that is realized by train- ing two models that learn visual features via coop- erative reconstruction, but one model is adversari- ally dissociated from the reward signal. Empirical evaluation shows that TIA leads to significant per- formance gains over state-of-the-art methods on many visual control tasks where natural and un- constrained visual distractions pose a formidable challenge. Project page: https://xiangfu.co/tia 

Bioremediation is the use of microorganisms for the degradation or removal of contaminants. Most bioremediation research has focused on processes performed by the domain Bacteria ; however, Archaea are known to play important roles in many situations. In extreme conditions, such as halophilic or acidophilic environments, Archaea are well suited for bioremediation. In other conditions, Archaea collaboratively work alongside Bacteria during biodegradation. In this review, the various roles that Archaea have in bioremediation is covered, including halophilic hydrocarbon degradation, acidophilic hydrocarbon degradation, hydrocarbon degradation in nonextreme environments such as soils and oceans, metal remediation, acid mine drainage, and dehalogenation. Research needs are addressed in these areas. Beyond bioremediation, these processes are important for wastewater treatment (particularly industrial wastewater treatment) and help in the understanding of the natural microbial ecology of several Archaea genera.