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.
Adversarial imitation learning has become a popular framework for imitation in continuous control. Over the years, several variations of its components were proposed to enhance the performance of the learned policies as well as the sample complexity of the algorithm. In practice, these choices are rarely tested all together in rigorous empirical studies. It is therefore difficult to discuss and understand what choices, among the high-level algorithmic options as well as low-level implementation details, matter. To tackle this issue, we implement more than 50 of these choices in a generic adversarial imitation learning framework and investigate their impacts in a large-scale study (>500k trained agents) with both synthetic and human-generated demonstrations. While many of our findings confirm common practices, some of them are surprising or even contradict prior work. In particular, our results suggest that artificial demonstrations are not a good proxy for human data and that the very common practice of evaluating imitation algorithms only with synthetic demonstrations may lead to algorithms which perform poorly in the more realistic scenarios with human demonstrations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.00672")
get_code_for_paper("2106.00672")
have("2106.00672")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.00672.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.00672)
Connect an agent — have() is free.