Nirnai Rao, Elie Aljalbout, Axel Sauer, Sami Haddadin
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In recent years, challenging control problems became solvable with deep reinforcement learning (RL). To use RL for large-scale real-world applications, a certain degree of reliability in their performance is necessary. Reported results of state-of-the-art algorithms are often difficult to reproduce. One reason for this is that certain implementation details influence the performance significantly. Commonly, these details are not highlighted as important techniques to achieve stateof-the-art performance. Additionally, techniques from supervised learning are often used by default but influence the algorithms in a reinforcement learning setting in different and not well-understood ways. In this paper, we investigate the influence of certain initialization, input normalization, and adaptive learning techniques on the performance of state-of-the-art RL algorithms. We suggest which of those techniques to use by default and highlight areas that could benefit from a solution tailored explicitly to RL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.13083")
get_code_for_paper("2010.13083")
have("2010.13083")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2010.13083.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2010.13083)
Connect an agent — have() is free.