Simple random search provides a competitive approach to reinforcement learning · HackerPapers discussions

Simple random search provides a competitive approach to reinforcement learning — mentioned by erwincoumans

Thu, 09 Jun 2022 20:25:06 GMT

Black box optimization such as CMA-ES or Augmented Random Search (ars) are used by researchers, for example: CMA-ES: https://blog.otoro.net/2017/10/29/visual-evolution-strategie... ARS: https://arxiv.org/abs/1803.07055 Those optimizers are efficient up to certain neural network sizes.

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

Simple random search provides a competitive approach to reinforcement learning — HN submission

Sat, 24 Aug 2019 19:26:08 GMT

Simple random search provides a competitive approach to reinforcement learning

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple random search provides a competitive approach to reinforcement learning — mentioned by rademacher

Fri, 09 Nov 2018 13:54:18 GMT

DRL has definitely shown some excellent results but can someone in the field comment on this paper, Simple random search provides a competitive approach to reinforcement learning [1]. [1] https://arxiv.org/abs/1803.07055

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

Simple random search provides a competitive approach to reinforcement learning — mentioned by naturalgradient

Mon, 25 Jun 2018 14:33:31 GMT

So as someone working in reinforcement learning who has used PPO a fair bit, I find this quite disappointing from an algorithmic perspective. The resources used for this are almost absurd and my suspicion is, especially considering [0], that this comes down to an incredibly expensive random search in the policy space. Or rather, I would want to see a fair bit of analysis to be shown otherwise. Especially given all the work in intrinsic motivation, hierarchical learning, subtask learning, etc, the sort of intermediate summary of most of these papers from 2015-2018 is that so many of these…

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

Simple random search provides a competitive approach to reinforcement learning — HN submission

Mon, 25 Jun 2018 02:25:26 GMT

Simple random search provides a competitive approach to reinforcement learning

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple random search provides a competitive approach to reinforcement learning — HN submission

Fri, 13 Apr 2018 16:43:03 GMT

Simple random search provides a competitive approach to reinforcement learning

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple random search provides a competitive approach to reinforcement learning — HN submission

Wed, 21 Mar 2018 04:40:25 GMT

Simple Random Search provides a competitive approach to RL

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple random search provides a competitive approach to reinforcement learning — HN submission

Tue, 20 Mar 2018 19:19:25 GMT

Simple random search provides a competitive approach to reinforcement learning

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple random search provides a competitive approach to reinforcement learning — HN submission

Tue, 20 Mar 2018 00:45:58 GMT

Simple random search provides a competitive approach to reinforcement learning

8 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.