-
---
**Issue Description:**
When executing the `sh scripts/train_autophase_offline_q_value_rank.sh` script, I encounter the following error:
```
Error executing job with overrides: ['seed=2…
chhnb updated
5 months ago
-
I am getting the following error
`(CompileError) deps/axon/lib/axon/loop.ex:469: the do-block in while must return tensors with the same shape, type, and names as the initial arguments.`
While t…
-
I am referring to the gradient derivation [here](https://huggingface.co/learn/deep-rl-course/unit4/pg-theorem#optional-the-policy-gradient-theorem).
The paragraph where the instructor claimed "we c…
-
The link is on the word "here" just above "Implementing Reward-to-Go Policy Gradient" (scroll one line up from: https://spinningup.openai.com/en/latest/spinningup/rl_intro3.html#implementing-reward-to…
-
ImportError Traceback (most recent call last)
in ()
2 import tensorflow as tf
3 import numpy as np
----> 4 from policy_gradient import util
5 from poli…
-
Hi, I want to ask that when training on DynamicViT at keep ratio **0.3**, the training will terminate due to loss nan problem, my training script is shown below.
Since I remember the original Dynami…
-
Hi there,
I noticed that even though policy net and value net share some parameters (in a3c/estimators.py), their gradient were [clipped](https://github.com/dennybritz/reinforcement-learning/blob/m…
-
Currently, tianshou sets the policy's mode in the trainer and `test_episode` function. The corresponding `training` attribute is then used to determine if a stochastic policy should be evaluated deter…
-
I replicated the experiments of pythia28 on hh (Anthropic/hh-rlhf) using the open-source code. Here are some of the experimental results:
**SFT1**:
~~~
python -u train.py exp_name=sft gradient_ac…
-
In each policy update step, the penalty function is called with the policy and the current state. this results in a gradient.
Currently i have two ideas for such a penalty function, both need a (co…