-
Lately, there has been an explosion of interest in using Deep Reinforcement Learning to learn to play Atari 2600 games. I would like to get in on this trend by integrating this code into MM-NEAT. MM-N…
-
trying to hook it up to cartpole..
```py
print(self.env.reset())
(pid=2462395) [ 0.01369617 -0.02302133 -0.04590265 -0.04834723]
```
but it expects:
```py
obs, info = self.env.reset()
```
ie …
-
Hi,
This looks great. How would you go about and adapt this to Open AI Gym for example?
Can you please provide a set of places where changes have to be made?
How Generic is the code to adapt to any…
pranv updated
8 years ago
-
$pip install -r requirements.txt
Requirement already satisfied: atari-py==0.1.1 in ./curiosity/lib/python2.7/site-packages (from -r src/requirements.txt (line 1)) (0.1.1)
Requirement already satisfi…
-
In many places in the code, there's a hardwired expectation that the environment will either be from ALE, or else it will be from some other type of video game. This limits the usefulness of the RL al…
-
Hi there,
Below are logs and error messages I get when attempting the pip installation of mujoco-py.
I'm running OS X 10.10.5, in a conda env with python 3.5.2
```
`$ pip install mujoco-py
Co…
-
Hi, is the rewards and regret calculation necessary two times ?
1) In the step function of src/env.py, line number 97-99.
2) In train.py, line 101.
In both places, rewards and regrets are being c…
-
**Build an example using current code.** Use `reinforce-algorithms` to come up with an example of using the current algorithm interfaces (`Reinforce.Algorithms`), and the Q-Table "backend" (`Reinforce…
-
Please add some comments to the definition of the reinforcement learning models to understand, why they were designed like this.
Checklist
- [X] Modify `rl_gym_environments.py` ✓ https://github.co…
-
If VizDoom doesn't come as an openAI Gym, we may need to create a new episode runner for this
todo:
- [ ] investigate if vizdoom is compatible with our eprunner
- [ ] implement vizdoom (as a n…