Dota 2
Gathering human feedback
Better exploration with parameter noise
Proximal Policy Optimization
Robust adversarial inputs
Hindsight Experience Replay
Teacher–student curriculum learning
Faster physics in Python
Learning from human preferences
Learning to cooperate, compete, and communicate
Latest
Dota 2
9 years ago
19 Add to circle
Gathering human feedback
9 years ago
22 Add to circle
Better exploration with parameter noise
9 years ago
19 Add to circle
Proximal Policy Optimization
9 years ago
23 Add to circle
Robust adversarial inputs
9 years ago
22 Add to circle
Hindsight Experience Replay
9 years ago
22 Add to circle
Teacher–student curriculum learning
9 years ago
20 Add to circle
Faster physics in Python
9 years ago
21 Add to circle
Learning from human preferences
9 years ago
20 Add to circle
Learning to cooperate, compete, and communicate
9 years ago
25 Add to circle
UCB exploration via Q-ensembles
9 years ago
20 Add to circle
OpenAI Baselines: DQN
9 years ago
23 Add to circle
Robots that learn
9 years ago
19 Add to circle
Roboschool
9 years ago
18 Add to circle
Unsupervised sentiment neuron
9 years ago
22 Add to circle
Spam detection in the physical world
9 years ago
21 Add to circle
English (US)