Industry
Decentralized Learning in Online Queuing Systems
Inefficient decisions in repeated games can stem from both strategic and learning considerations. First, strategic agents selfishly maximize their own individual reward at others' expense.
Decentralized Learning in Online Queuing Systems
Inefficient decisions in repeated games can stem from both strategic and learning considerations. First, strategic agents selfishly maximize their own individual reward at others' expense.
Scalarization for Multi-Task and Multi-Domain Learning at Scale Amélie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi Qualcomm AI Research Amsterdam, The Netherlands
It also enables potential positive knowledge transfer across tasks/domains, leading to improved accuracy and data-efficient training.
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Continual learning agents experience a stream of (related) tasks.
Checklist 1. For all authors (a)
Do the main claims made in the abstract and introduction accurately reflect the paper's Did you discuss any potential negative societal impacts of your work? If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Y es] Available at Did you specify all the training details (e.g., data splits, hyperparameters, how they Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? Appendix 4. If you are using existing assets (e.g., code, data, models) or curating/releasing new assets... (a) If your work uses existing assets, did you cite the creators? Did you include any new assets either in the supplemental material or as a URL? [No] Did you discuss whether and how consent was obtained from people whose data you're If you used crowdsourcing or conducted research with human subjects... (a) Our method proposes to learn efficient data structure for accurate prediction in large-output space.
Autonomous Reinforcement Learning via Subgoal Curricula
Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents.
A General Implementation Details For our Atari games and DeepMind Control Suite experiments, we largely follow DrQ [ 33
The replay buffer size is 100K. This procedure is repeated every time an image is sampled from the replay buffer. Batch size used in both RL and representation learning is 512. The corresponding hyperparameters used in Atari experiments are shown in Table 7 and Table 8. The action repeat hyperparameters are show in Table 6.
Behavior From the Void: Unsupervised Active Pre-Training
We empirically evaluate APT by exposing task-specific reward after a long unsupervised pre-training phase.
