Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
Blokirali ste korisnika/cu @sagarpath
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @sagarpath
-
Sagar Pathrudkar proslijedio/la je Tweet
To the left, you see a trained agent playing a level of a game. To the right, you see the same playthrough from an agent-centric perspective: cropped, translated, and rotated with the agent in the center. Which perspective is the best input for the agent? https://arxiv.org/abs/2001.09908 pic.twitter.com/7bCtBp8xUG
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
BlenderProc generates visual data for training CNNs including depth, normals, semantic segmentation, pose annotations, and of course color images and much more! Code: https://github.com/DLR-RM/BlenderProc …pic.twitter.com/U8UbAbNElk
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
The benefits of synthetic data for action categorization https://arxiv.org/abs/2001.11091 pic.twitter.com/XVSthnUx2e
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Humans learn from curriculum since birth. We can learn complicated math problems because we have accumulated enough prior knowledge. This could be true for training a ML/RL model as well. Let see how curriculum can help an RL agent learn:https://lilianweng.github.io/lil-log/2020/01/29/curriculum-for-reinforcement-learning.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
PolyGame: An open-source framework for training AI players through self-play. Deals with many games, board size variation, partial observability... Interesting generalization tidbit: It plays Go on 19x19 at very good level after training only on 13x13.https://ai.facebook.com/blog/open-sourcing-polygames-a-new-framework-for-training-ai-bots-through-self-play/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
ML Fairness Gym is a set of components for building simple simulations that explore the potential long-run impacts of deploying machine learning-based decision systems in social environments, based on OpenAI Gym interface.https://github.com/google/ml-fairness-gym …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
New paper: Towards a Human-like Open-Domain Chatbot. Key takeaways: 1. "Perplexity is all a chatbot needs" ;) 2. We're getting closer to a high-quality chatbot that can chat about anything Paper: https://arxiv.org/abs/2001.09977 Blog: https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html …pic.twitter.com/5SOBa58qx3
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
In “Artificial Intelligence, Values and Alignment” DeepMind’s
@IasonGabriel explores approaches to aligning AI with a wide range of human values: https://deepmind.com/research/publications/Artificial-Intelligence-Values-and-Alignment …pic.twitter.com/Zo81PSpwyF
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Check out Meena, a new state-of-the-art open-domain conversational agent, released along with a new evaluation metric, the Sensibleness and Specificity Average, which captures basic, but important attributes for normal conversation. Learn more below!https://goo.gle/36zB8Wj
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
What if we see level generation as a game, where each action changes the level in some way? Well, we could use RL to learn to "play" level generation! We introduce Procedural Content Generation via Reinforcement Learning (PCGRL), a new paradigm for PCG. https://arxiv.org/abs/2001.09212 pic.twitter.com/J9c8O5EIM7
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Procedural Content Generation via Reinforcement Learning “A new approach to procedural content generation in games, where level design is framed as a game (as a sequential task problem), and the content generator itself is learned.” https://arxiv.org/abs/2001.09212 pic.twitter.com/2B6P6tlh9d
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Quaternions and Euler angles are discontinuous and difficult for neural networks to learn. They show 3D rotations have continuous representations in 5D and 6D, which are more suitable for learning. i.e. regress two vectors and apply Graham-Schmidt (GS). https://arxiv.org/abs/1812.07035 pic.twitter.com/fXUF3sgkTT
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Impressive results on single image depth estimation by Ranftl et al https://arxiv.org/abs/1907.01341 pic.twitter.com/f6nrhXyCCH
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Q-learning is difficult to apply when the number of available actions is large. We show that a simple extension based on amortized stochastic search allows Q-learning to scale to high-dimensional discrete, continuous or hybrid action spaces: https://arxiv.org/abs/2001.08116
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
@PyTorch code showing the generic learning setup and reproducing simple experiments is now available! Code: https://github.com/nv-tlabs/meta-sim … Project Page: https://nv-tlabs.github.io/meta-sim/ Paper: https://arxiv.org/abs/1904.11621 https://twitter.com/FidlerSanja/status/1122997150550564864 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Excited to release our work on MetaSim which learns to generate synthetic datasets that resemble real datasets in content.
@NvidiaAI@amlankar95@aayush382@liu_mingyu@davidjesusacu Antonio Torralba etc paper: https://arxiv.org/abs/1904.11621 project page: https://nv-tlabs.github.io/meta-sim/ pic.twitter.com/DeuxFwSQvxPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Excited to share PCGrad, a super simple & effective method for multi-task learning & multi-task RL: project conflicting gradients On Meta-World MT50, PCGrad can solve *2x* more tasks than prior methods https://arxiv.org/abs/2001.06782 w/ Tianhe Yu, S Kumar, Gupta,
@svlevine,@hausman_kpic.twitter.com/uTeUhULUTA
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
We’re releasing a major update to Facebook AI’s open source AI Habitat platform for training embodied AI agents in photorealistic 3D virtual environments. AI Habitat now supports interactive objects, realistic physics modeling, and more. https://ai.facebook.com/blog/ai-habitat-state-of-the-art-simulation-platform-adds-object-interactivity/ …pic.twitter.com/YDx0EZSZ2v
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Facebook AI has effectively solved the task of point-goal navigation by AI agents in simulated environments, using only a camera, GPS, and compass data. Agents achieve 99.9% success in a variety of virtual settings, such as houses and offices. https://ai.facebook.com/blog/near-perfect-point-goal-navigation-from-25-billion-frames-of-experience/ …pic.twitter.com/Cogyp90CwW
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sagar Pathrudkar proslijedio/la je Tweet
Given the smoothness of videos, can we learn models more efficiently than with
#backprop? We present Sideways - a step towards a high-throughput, approximate backprop that considers the one-way direction of time and pipelines forward and backward passes. https://arxiv.org/pdf/2001.06232.pdf …pic.twitter.com/evbwULE0s2Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.