Frank Wood, Mark Schmidt, Andrew Warrington, J Wilder Lavington, Adam Ścibior
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.
Policies for partially observed Markov decision processes can be efficiently learned by imitating expert policies learned using asymmetric information. Unfortunately, existing approaches for this kind of imitation learning have a serious flaw: the expert does not know what the trainee cannot see, and may therefore encourage actions that are sub-optimal or unsafe under partial information. To address this flaw, we derive an update that, when applied iteratively to an expert, maximizes the expected reward of the trainee's policy. Using this update, we construct a computationally efficient algorithm, adaptive asymmetric DAgger (A2D), that jointly trains the expert and trainee policies. We then show that A2D allows the trainee to safely imitate the modified expert, and outperforms policies learned either by imitating a fixed expert or direct reinforcement learning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.15566")
get_code_for_paper("2012.15566")
have("2012.15566")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.15566.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.15566)
Connect an agent — have() is free.