Ruslan Salakhutdinov, Nitish Srivastava, Hanlin Goh, Yue Wu, Jian Zhang, Shuangfei Zhai, Joshua Susskind
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.
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and actor-critic based off-policy RL algorithms fail when bootstrapping from out-of-distribution (OOD) actions or states. We hypothesize that a key missing ingredient from the existing methods is a proper treatment of uncertainty in the offline setting. We propose Uncertainty Weighted Actor-Critic (UWAC), an algorithm that detects OOD state-action pairs and down-weights their contribution in the training objectives accordingly. Implementation-wise, we adopt a practical and effective dropout-based uncertainty estimation method that introduces very little overhead over existing RL algorithms. Empirically, we observe that UWAC substantially improves model stability during training. In addition, UWAC out-performs existing offline RL methods on a variety of competitive tasks, and achieves significant performance gains over the state-of-the-art baseline on datasets with sparse demonstrations collected from human experts.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2105.08140")
get_code_for_paper("2105.08140")
have("2105.08140")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2105.08140.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2105.08140)
Connect an agent — have() is free.