User contributions for Isucholu
Jump to navigation
Jump to search
23 February 2018
- 00:4600:46, 23 February 2018 diff hist +2 One-Shot Imitation Learning →One-Shot Imitation Learning
- 00:4500:45, 23 February 2018 diff hist +1,916 One-Shot Imitation Learning →Neighborhood Attention:
- 00:0000:00, 23 February 2018 diff hist +239 One-Shot Imitation Learning →References
22 February 2018
- 23:5623:56, 22 February 2018 diff hist +1,394 One-Shot Imitation Learning →Criticisms
- 23:4223:42, 22 February 2018 diff hist +1,477 One-Shot Imitation Learning →Context network
- 23:0523:05, 22 February 2018 diff hist +320 One-Shot Imitation Learning →Performance Evaluation
- 23:0023:00, 22 February 2018 diff hist +486 N File:oneshot3.jpg From [https://papers.nips.cc/paper/6709-one-shot-imitation-learning.pdf (Duan et al. 2017)] Figure 3: Comparison of different conditioning strategies. The darkest bar shows the performance of the hard-coded policy, which unsurprisingly performs the bes... current
- 22:5922:59, 22 February 2018 diff hist +1,565 One-Shot Imitation Learning →Experiments
- 18:3618:36, 22 February 2018 diff hist +399 One-Shot Imitation Learning →Conclusions
- 17:4217:42, 22 February 2018 diff hist +15 One-Shot Imitation Learning →Neighborhood Attention:
- 17:4017:40, 22 February 2018 diff hist +2 One-Shot Imitation Learning →Architecture
- 17:4017:40, 22 February 2018 diff hist −1 One-Shot Imitation Learning →Architecture
- 17:3917:39, 22 February 2018 diff hist +161 One-Shot Imitation Learning →Manipulation network
- 17:3717:37, 22 February 2018 diff hist +911 One-Shot Imitation Learning →Demonstration Network
- 17:1317:13, 22 February 2018 diff hist +1,275 One-Shot Imitation Learning →Related Work
- 02:0002:00, 22 February 2018 diff hist +6 One-Shot Imitation Learning →Manipulation network
- 02:0002:00, 22 February 2018 diff hist +6 One-Shot Imitation Learning →Algorithm
- 01:5901:59, 22 February 2018 diff hist +143 N File:oneshot2.jpg From [https://papers.nips.cc/paper/6709-one-shot-imitation-learning.pdf (Duan et al. 2017)] Figure 2: Illustration of the network architecture. current
- 01:5801:58, 22 February 2018 diff hist +115 One-Shot Imitation Learning →Architecture
- 01:5201:52, 22 February 2018 diff hist +1,246 N File:oneshot1.jpg From [https://papers.nips.cc/paper/6709-one-shot-imitation-learning.pdf (Duan et al. 2017)] Figure 1: (a) Traditionally, policies are task-specific. For example, a policy might have been trained through an imitation learning algorithm to stack blocks i... current