-
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 :…
-
-
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…
-
Hi author, I ran the code [https://github.com/koryakinp/A2C](url), I modified the environment and just want to test it on the gym environment such as pong. While I got the **_NotImplementedError_** er…
-
Hello, I'm interested in your work.
However, I got some issues in here. It seems to be the problem of using Cartpole environment in the atari wrapper but I cannot find how to solve it without c…
-
I am trying to use debugging to figure out the process of A2C method in tf2 branch
so I add the code in a2c.py as follows:
`if __name__ == '__main__':
import gym
learn('mlp',gym.vector.ma…
-
I generated a game with a 10 * 10 map - pursuit. There are one predator with my own a2c model and two preys with random actor. By training, predator's total reward per episode converges to zero, never…
-
## 🚀 Feature
The RL section of bolts currently only includes variants of DQN and VPG and lacks some of the more modern RL algorithms. Adding PPO, A2C, curiosity exploration etc. might be prudent
-…
-
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
-
1. Where is 'processed_full' defined?
```
----> 1 data_risk_indicator = processed_full[(processed_full.date=TRAIN_START_DATE)]
2 insample_risk_indicator = data_risk_indicator.drop_duplicates…