-
您好,我直接使用demo_A2C_PPO.py训练pendulum环境下的A2C算法无法收敛,可能算法实现上有问题。AgentDiscreteA2C算法仅继承了AgentDiscretePPO,并未实现自己的update_net函数
-
hello,
i get this error, when i run code "python main.py --env-name "PongNoFrameskip-v4"
i don't know what happed, my env is:
python3.6.3
Package Version
----------------- -------
a…
-
I wrote an A2C have the same problem, is the problem of A2C?
-
**Describe the bug**
Pwnagotchi went to AI in just few minutes but upon checking it does not save the brain in /root directory
**To Reproduce**
Steps to reproduce the behavior:
1. reboot and sta…
do-ki updated
8 months ago
-
I have a custom environment with a [MultiDiscrete](https://github.com/openai/gym/blob/master/gym/spaces/multi_discrete.py) action space. The MultiDiscrete action space allows controlling an agent with…
-
执行
`python demo_A2C_PPO.py --gpu=0 --drl=0 --env=6`
出现异常
```
File "elegantrl/train/evaluator.py", line 176, in get_cumulative_rewards_and_steps
tensor_action = tensor_action.argmax(dim=1)
In…
-
I have cuda installed. I have given "device": "cuda" in params but I am still getting using cpu device.
`A2C_PARAMS = {"n_steps": 5, "ent_coef": 0.01, "learning_rate": 0.0005, "device": "cuda"}`
o…
-
Hello Jacob or anybody who can answer the question,
Thank you for your repository.
I am a beginner on reinforcement learning and have a very basic problem if you could put some light on it.
I…
-
Hello.
I firstly change the policy in by:
`parser.add_argument('--policy', help='Policy architecture', choices=['cnn', 'lstm', 'lnlstm'], default='lstm')`
Then I run A2C+SIL on Atari games :…
-
A2C와 A4C 데이터셋을 위한 모델을 각각 두개로 나누어 사용해도 되나요?
아니면 A2C와 A4C 모두 같은 모델로 진행해야 하나요?