Relational Deep Reinforcement Learning — mentioned by taliesinb

Sun, 18 Aug 2019 10:17:40 GMT

Hasselt and co, who authored the original Rainbow DQN model that was bested by SimPLe (this paper), responded recently with "When to use parametric models in reinforcement learning?" [1], which is an interesting read. Punchline: "We explain why their [SimPLe's] results may perhaps be considered surprising, and show that in a like-for-like comparison Rainbow DQN outperformed the scores of the model-based agent, with less experience and computation.". In other words, in an apples-to-apples comparison, model-based RL have not been shown to be more sample efficient than suitably optimized DQNs.…

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

Relational Deep Reinforcement Learning — mentioned by yonkshi

Mon, 24 Dec 2018 02:50:23 GMT

Sure. I don't have any holistic survey to prove my point, but an example of recent progress in terms of sample efficiency is this paper[0]. Derivatives of this paper have been used to solve Sudoku[1], Starcraft II[2] and more [3]. This paper enabled more efficient use of data by creating a probabilistic graphical model between logical sets. [0]https://arxiv.org/abs/1706.01427 [1]https://arxiv.org/abs/1711.08028 [2]https://arxiv.org/abs/1806.01830 [3]https://arxiv.org/abs/1806.01822

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

Relational Deep Reinforcement Learning · HackerPapers discussions

Relational Deep Reinforcement Learning — mentioned by taliesinb

Relational Deep Reinforcement Learning — mentioned by yonkshi