-
Hi,
In your SAC docs it says
> An alternate version of SAC, which slightly changes the policy update rule, can be implemented to handle discrete action spaces.
I was then wondering if you kne…
-
RuntimeError: expected CPU tensor (got CUDA tensor)
It shows the above message when I give it a CPU tensor rather than a CUDA tensor. What I mean to say is, the error should have been
RuntimeEr…
-
Hi,
I'm trying to load your pre-trained DQN Breakout agent into a PyTorch network. I have figured out how to get the weights transferred over but the pytorch agent is still not able to do well on …
-
DQN is supposed to be a fairly basic Deep RL agent, so we should be able to get it working and running using PyTorch, and applied to Open AI Gym domains. The code from that Grokking RL Repo should wor…
-
Hello, I am recently running your code in ubuntu16.04, ros kinetic, and v-rep 3.6.1. When I start the simulation of V-rep scene, and run the command "python main.py --is_train=True" to perform trainin…
-
Deay guys,
I'm am trying train crnn model, but I always meet these errors:
Traceback (most recent call last):
File "crnn_main.py", line 201, in
cost = trainBatch(crnn, criterion, optimize…
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: WSL Ubuntu 18.04
- **Ray installed from (source or binary)**: Source
- **Ray version**: 0.7.0.dev1
- **Python…
-
======================================================================
FAIL: test_trainer_maxq (ml.rl.test.constant_reward.test_constant_reward.TestConstantReward)
----------------------------------…
-
We should implement / port a DQN for PyTorch.
ericl updated
5 years ago
-
This issue will be used to track 0.7.2 release.
- [x] bump version to `0.7.2` (#5066)
- In `python/ray/__init.py`: (#5066)
- In `src/ray/raylet/main.cc`: (#5070)
- [x] bump version to `0.…