-
Hi i am considering adjusting the solver for solving plo4. Can you please tell me if you think it would be easy, and if you could recommend something for reading how solver algorithm works?
-
Hi, @jprothero
It's great to see another deep learning enthusiast. Greetings.
You can call me Yohan, I am a junior year Math student at University of illinois. You can email me `hangyu5@illinois.…
-
1. In dlgo.agent.alphago.AlphaGoMCTS we have the policy rollout function in line 142.
```
def policy_rollout(self, game_state):
for step in range(self.rollout_limit):
if game_…
-
self._u = (c_puct * self._P *np.sqrt(self._parent._n_visits) / (1 + self._n_visits))
是不是要改成下面的:
self._u = (c_puct * self._P *np.sqrt(self._parent._n_visits / (1 + self._n_visits)))
self._parent._…
tianv updated
6 years ago
-
# Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning #
- Author: Xiaoxiao Guo, Satinder Singh, Honglak Lee, Richard L. Lewis, Xiaoshi Wang
- Origin: https:/…
-
@cooijmanstim
Hi, I am python programmer who started a [alphaGo Zero replication project](https://github.com/yhyu13/AlphaGOZero-python-tensorflow/tree/py2.7), I would like to practice a similar de…
-
Source: https://deepmind.com/blog/article/AlphaStar-Grandmaster-level-in-StarCraft-II-using-multi-agent-reinforcement-learning
Ref2: https://aisc.ai.science/events/2019-12-09
Problems:
StarC…
-
@AnneCarpenter raised the point in #201 that we should discuss specific examples of deep learning successes. Which specific examples do we want to highlight. I think the results related to image analy…
-
I would like to use KotlinDL to create a AlphaZero like dual head network for my game.
Unfortunately I haven't found any hint on how to accomplish that.
Is this already possible or would it be…
-
Hi,
I was just curious how move evaluations are meant to be used? In the counting game example, the evaluation returns a vector of `()` for each move, and just returns a state evaluation instead.
…