RSS

New Topic

1139 topics

Page 44 of 46
- Jump to page:
Previous
1
…
42
43
44
45
46
Next

Topics

Replies

Views

Last post

OPEN AI Asymmetric actor critic for image-based robot learning

Last post by admin « Wed Oct 18, 2017 7:00 am

by admin » Wed Oct 18, 2017 7:00 am

Asymmetric actor critic for image-based robot learning

Source:

0 Replies

13 Views

Last post by admin
Wed Oct 18, 2017 7:00 am
OPEN AI Domain randomization and generative models for robotic grasping

Last post by admin « Tue Oct 17, 2017 7:00 am

by admin » Tue Oct 17, 2017 7:00 am

Domain randomization and generative models for robotic grasping

Source:

0 Replies

12 Views

Last post by admin
Tue Oct 17, 2017 7:00 am
OPEN AI Meta-learning for wrestling

Last post by admin « Wed Oct 11, 2017 7:00 am

by admin » Wed Oct 11, 2017 7:00 am

We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and...

0 Replies

12 Views

Last post by admin
Wed Oct 11, 2017 7:00 am
OPEN AI Competitive self-play

Last post by admin « Wed Oct 11, 2017 7:00 am

by admin » Wed Oct 11, 2017 7:00 am

We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the...

0 Replies

14 Views

Last post by admin
Wed Oct 11, 2017 7:00 am
OPEN AI Nonlinear computation in deep linear networks

Last post by admin « Fri Sep 29, 2017 7:00 am

by admin » Fri Sep 29, 2017 7:00 am

Nonlinear computation in deep linear networks

Source:

0 Replies

15 Views

Last post by admin
Fri Sep 29, 2017 7:00 am
OPEN AI Learning to model other minds

Last post by admin « Thu Sep 14, 2017 7:00 am

by admin » Thu Sep 14, 2017 7:00 am

We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative...

0 Replies

11 Views

Last post by admin
Thu Sep 14, 2017 7:00 am
OPEN AI Learning with opponent-learning awareness

Last post by admin « Wed Sep 13, 2017 7:00 am

by admin » Wed Sep 13, 2017 7:00 am

Learning with opponent-learning awareness

Source:

0 Replies

13 Views

Last post by admin
Wed Sep 13, 2017 7:00 am
OPEN AI OpenAI Baselines: ACKTR & A2C

Last post by admin « Fri Aug 18, 2017 7:00 am

by admin » Fri Aug 18, 2017 7:00 am

We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor...

0 Replies

16 Views

Last post by admin
Fri Aug 18, 2017 7:00 am
OPEN AI More on Dota 2

Last post by admin « Wed Aug 16, 2017 7:00 am

by admin » Wed Aug 16, 2017 7:00 am

Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given...

0 Replies

10 Views

Last post by admin
Wed Aug 16, 2017 7:00 am
OPEN AI Dota 2

Last post by admin « Fri Aug 11, 2017 7:00 am

by admin » Fri Aug 11, 2017 7:00 am

We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from...

0 Replies

12 Views

Last post by admin
Fri Aug 11, 2017 7:00 am
OPEN AI Gathering human feedback

Last post by admin « Thu Aug 03, 2017 7:00 am

by admin » Thu Aug 03, 2017 7:00 am

RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions....

0 Replies

16 Views

Last post by admin
Thu Aug 03, 2017 7:00 am
OPEN AI Better exploration with parameter noise

Last post by admin « Thu Jul 27, 2017 7:00 am

by admin » Thu Jul 27, 2017 7:00 am

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method...

0 Replies

9 Views

Last post by admin
Thu Jul 27, 2017 7:00 am
OPEN AI Proximal Policy Optimization

Last post by admin « Thu Jul 20, 2017 7:00 am

by admin » Thu Jul 20, 2017 7:00 am

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than...

0 Replies

14 Views

Last post by admin
Thu Jul 20, 2017 7:00 am
OPEN AI Robust adversarial inputs

Last post by admin « Mon Jul 17, 2017 7:00 am

by admin » Mon Jul 17, 2017 7:00 am

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last...

0 Replies

14 Views

Last post by admin
Mon Jul 17, 2017 7:00 am
OPEN AI Hindsight Experience Replay

Last post by admin « Wed Jul 05, 2017 7:00 am

by admin » Wed Jul 05, 2017 7:00 am

Hindsight Experience Replay

Source:

0 Replies

17 Views

Last post by admin
Wed Jul 05, 2017 7:00 am
OPEN AI Teacher–student curriculum learning

Last post by admin « Sat Jul 01, 2017 7:00 am

by admin » Sat Jul 01, 2017 7:00 am

Teacher–student curriculum learning

Source:

0 Replies

13 Views

Last post by admin
Sat Jul 01, 2017 7:00 am
OPEN AI Faster physics in Python

Last post by admin « Wed Jun 28, 2017 7:00 am

by admin » Wed Jun 28, 2017 7:00 am

We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics...

0 Replies

13 Views

Last post by admin
Wed Jun 28, 2017 7:00 am
OPEN AI Learning from human preferences

Last post by admin « Tue Jun 13, 2017 7:00 am

by admin » Tue Jun 13, 2017 7:00 am

One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or...

0 Replies

16 Views

Last post by admin
Tue Jun 13, 2017 7:00 am
OPEN AI Learning to cooperate, compete, and communicate

Last post by admin « Thu Jun 08, 2017 7:00 am

by admin » Thu Jun 08, 2017 7:00 am

Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful...

0 Replies

12 Views

Last post by admin
Thu Jun 08, 2017 7:00 am
OPEN AI UCB exploration via Q-ensembles

Last post by admin « Mon Jun 05, 2017 7:00 am

by admin » Mon Jun 05, 2017 7:00 am

UCB exploration via Q-ensembles

Source:

0 Replies

11 Views

Last post by admin
Mon Jun 05, 2017 7:00 am
OPEN AI OpenAI Baselines: DQN

Last post by admin « Wed May 24, 2017 7:00 am

by admin » Wed May 24, 2017 7:00 am

We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published...

0 Replies

14 Views

Last post by admin
Wed May 24, 2017 7:00 am
OPEN AI Robots that learn

Last post by admin « Tue May 16, 2017 7:00 am

by admin » Tue May 16, 2017 7:00 am

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done...

0 Replies

14 Views

Last post by admin
Tue May 16, 2017 7:00 am
OPEN AI Roboschool

Last post by admin « Mon May 15, 2017 7:00 am

by admin » Mon May 15, 2017 7:00 am

We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.

Source:

0 Replies

13 Views

Last post by admin
Mon May 15, 2017 7:00 am
OPEN AI Equivalence between policy gradients and soft Q-learning

Last post by admin « Fri Apr 21, 2017 7:00 am

by admin » Fri Apr 21, 2017 7:00 am

Equivalence between policy gradients and soft Q-learning

Source:

0 Replies

11 Views

Last post by admin
Fri Apr 21, 2017 7:00 am
OPEN AI Stochastic Neural Networks for hierarchical reinforcement learning

Last post by admin « Mon Apr 10, 2017 7:00 am

by admin » Mon Apr 10, 2017 7:00 am

Stochastic Neural Networks for hierarchical reinforcement learning

Source:

0 Replies

12 Views

Last post by admin
Mon Apr 10, 2017 7:00 am

New Topic

1139 topics

Page 44 of 46
- Jump to page:
Previous
1
…
42
43
44
45
46
Next

Return to Board Index

Forum permissions

You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum