-
# HIL-SERL in LeRobot
---
On porting [HIL-SERL](https://hil-serl.github.io/) to LeRobot. This page will outline the minimal list of components and tasks that should be implemented in the LeRobot c…
-
https://arxiv.org/abs/1704.06676
TMats updated
7 years ago
-
- Matthew Hausknecht, Peter Stone
- Submitted on 23 Jul 2015 (v1), last revised 11 Jan 2017 (this version, v4)
TMats updated
6 years ago
-
-
-
If we have a discrete space, discrete action, generative MDP.
And states space and actions space are hard to enumerate. But we still want to use the traditional tabular RL algorithm to solve it.
So…
-
Can I know if there's a recommended dataset size that is ideal for the model to converge? I have been training the model (both from scratch and using the pretrained doctamper model) using about 600+ I…
hnsa9 updated
1 month ago
-
It seems like the Q-learner 'learn'-function inner for loop doesn't process the last state-action-reward tuple in the sequence. For example, if we have a sequence of actions from an episodic task, I w…
-
I am receiving the following error: `Expected q_network to emit a floating point tensor with inner dims (464,); but saw network output spec: TensorSpec(shape=(6, 4, 464), dtype=tf.float32, name=None)`…
-
## Agenda+: What do you want to discuss?
As a follow up of the presentation on Private Conversion Measurement via Global and Local DP (https://github.com/patcg/meetings/files/14936682/PATCG_Boston_…