Dileep Kalathil, Srinivas Shakkottai, Desik Rengarajan, Sapana Chaudhary, Jaewon Kim
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.
Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The metapolicy, when adapted over only a small (or just a single) number of steps, is able to perform near-optimally on a new, related task. However, a major challenge to adopting this approach to solve real-world problems is that they are often associated with sparse reward functions that only indicate whether a task is completed partially or fully. We consider the situation where some data, possibly generated by a suboptimal agent, is available for each task. We then develop a class of algorithms entitled Enhanced Meta-RL using Demonstrations (EMRLD) that exploit this information-even if sub-optimal-to obtain guidance during training. We show how EMRLD jointly utilizes RL and supervised learning over the offline data to generate a meta-policy that demonstrates monotone performance improvements. We also develop a warm started variant called EMRLD-WS that is particularly efficient for sub-optimal demonstration data. Finally, we show that our EMRLD algorithms significantly outperform existing approaches in a variety of sparse reward environments, including that of a mobile robot.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2209.13048")
get_code_for_paper("2209.13048")
have("2209.13048")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2209.13048.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2209.13048)
Connect an agent — have() is free.