-
# Context
As part of the TrustLevel.io score we want to integrate a click-biat (elozano/bert-base-cased-clickbait-news) detection model.
# Tasks
- [ ] get model working locally
- [ ] briefly test mod…
-
A clear metric should be given for every user to determine this status for greater transparency.
-
Hi Marc,
Amazing work! I wonder if there is any chance that you could share the code for generating the stochastic Mujoco dataset or give a hint of how this could be achieved with D4RL. Thank you v…
-
- [ ] I have marked all applicable categories:
+ [ ] exception-raising bug
+ [ ] RL algorithm bug
+ [ ] documentation request (i.e. "X is missing from the documentation.")
+ [x] ne…
-
### 🐛 Bug
Can be fixed easily, see #1439
### To Reproduce
```python
env = gym.make("Pendulum-v1")
model = SAC("MlpPolicy", env, verbose=1)
model.policy = th.compile(model.policy) # Com…
-
For multiple adapter PPO process, the reward adapter is loaded with `requires_grad=False`. In standard PPO process, the critic model is initialized with the loaded reward model but can still be update…
-
## Keyword: sgd
There is no result
## Keyword: optimization
### A Model-Constrained Tangent Manifold Learning Approach for Dynamical Systems
- **Authors:** Authors: Hai Van Nguyen, Tan Bui-Thanh
-…
-
in FinRL_single_stock_trading.ipynb
after finishing training Model 4 Sac I am getting this:
Model 4: SAC
agent = DRLAgent(env = env_train)
SAC_PARAMS = {
"batch_size": 128,
"buffer_s…
-
I tried an example with pole cart and the starter code with the provided FIFO on-policy replay buffer with PPO. There is an error regarding the cumulative reward.
With `FIFOOnPolicyReplayBuffer` a…
-
# Describe the bug
A clear and concise description of what the bug is.
**Please share your notebook link so that we can reproduce the error**
I have a model trained for the Actor Critic model i…