Constrained Policy Optimization — mentioned by gwern

Sat, 03 Jun 2017 16:51:35 GMT

> It would be nice to be able to define a prior that puts very low to no probability on actions that are not physically possible. This would constrain the search space considerably. But it's not really clear how to do this with neural nets. I dunno, I can think of several ways off the top of my head: 1. put large negative rewards on impossible actions; 2. only compute Q-values for feasible actions (just because DQN computes Q-values for a hardcoded set of actions doesn't mean you have to); 3. use Achiam's "Constrained Policy Optimization" https://arxiv.org/abs/1705.10528 ; 4. reparameterize…

Paper and discussion history. A mention is not an endorsement.

Constrained Policy Optimization · HackerPapers discussions

Constrained Policy Optimization — mentioned by gwern