user avatar
user avatar
user avatar
BigBadMe
  • Member for 3 years, 7 months
  • Last seen more than 1 year ago
4 votes
1 answer
740 views

How does DeepMind perform reinforcement learning on a TPU?

4 votes
1 answer
293 views

How do updates in SARSA and Q-learning differ in code?

4 votes
1 answer
58 views

How should I encode a categorical input?

4 votes
1 answer
286 views

In Monte Carlo learning, what do you do when an end state is reached, after having recorded the previously visited states and taken actions?

3 votes
1 answer
2k views

How to deal with the terminal state in SARSA in a multi-agent setting?

3 votes
1 answer
135 views

Can A3C update the policy / critic on a local machine without needing to copy?

2 votes
1 answer
126 views

What is the next state for a two-player board game?

2 votes
1 answer
33 views

Adding input features - is complete re-training required?

0 votes
0 answers
258 views

How to back-propagate illegal actions for policy gradient learning