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.
Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following this result, there have been several papers showing reasonable performances under a variety of environments and batch settings. In this paper, we benchmark the performance of recent off-policy and batch reinforcement learning algorithms under unified settings on the Atari domain, with data generated by a single partially-trained behavioral policy. We find that under these conditions, many of these algorithms underperform DQN trained online with the same amount of data, as well as the partially-trained behavioral policy. To introduce a strong baseline, we adapt the Batch-Constrained Q-learning algorithm to a discrete-action setting, and show it outperforms all existing algorithms at this task.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1910.01708")
get_code_for_paper("1910.01708")
have("1910.01708")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1910.01708.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1910.01708)
Connect an agent — have() is free.