-
## Motivation
In the current implementation of the VMAS environment, the done fields are only available on the root of the tensordict. However, for training, it is useful to have them in the group-…
-
C:\Users\hp\.conda\envs\py39\python.exe D:\DaiMa\DDPG-RIS-MADDPG-POWER-main\marl_test.py
------------- lanes are -------------
up_lanes : [200.875, 202.625, 400.875, 402.625]
down_lanes : [197.375…
-
### ❓ Question
When I try the code in intrinsic_reward_shaping.ipynb, I get an error.
The detailed error are as the following:
Traceback (most recent call last):
File "/home/x1/anaconda3/e…
-
When both use cpu in HalfCheetah-v2, the pytorch occupy about 1000% cpu and tensorflow only 300% cpu. But pytorch is much slower. When running 200000 timesteps, the pytorch costs about 1200s but tenso…
-
hi,jlubars
I'm sorry to trouble you,i need your help when i run this command,The following error has occurred
Traceback (most recent call last):
File "main.py", line 10, in
import ddpg
…
-
Currently, there is a working multi-agent PPO implementation here:
[https://github.com/matteobettini/rl/blob/mappo_ippo/examples/multiagent/mappo_ippo.py](url)
and a working single-agent DDPG impl…
-
### 🚀 Feature
independently configurable learning rates for actor and critic in AC-style algorithms
### Motivation
In literature the actor is often configured to learn slower, such that the c…
-
If I understand correctly, `d` comes from the environment and is not affected by `max_ep_len` or `ep_len` in the training loop so this line should not be necessary.
https://github.com/openai/spinni…
-
Hi, i read your code, and it is easy to understand, but there is one line of code that i'm confusing about. [https://github.com/transedward/pytorch-ddpg/blob/master/agents/ddpg_low_dim.py#L142](https:…
-
Traceback (most recent call last):
File "D:\Master\Codes\pytorch-ddpg\main.py", line 156, in
train(args.train_iter, agent, env, evaluate,
File "D:\Master\Codes\pytorch-ddpg\main.py", line …