Environments for Lifelong Reinforcement Learning

By Khimya Khetarpal, Shagun Sodhani, A. P. Sarath Chandar, Doina Precup. 2018

8 citations recorded by the source corpus.

To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific task but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned. In this paper, we discuss the desired characteristics of environments that can support the training and evaluation of lifelong reinforcement learning agents, review existing environments from this perspective, and propose recommendations for devising suitable environments in the future.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Roozbeh Mottaghi
2. Abhinav Kumar Gupta
3. Eric Kolve
4. Byeonghwi Kim
5. Minhyuk Seo
6. Jonghyun Choi
7. Sergey Levine
8. Eliot Xing

In Electrical and Electronic Engineering

1. Abhinav Kumar Gupta
2. Roozbeh Mottaghi

Citations in the corpus

• Online Continual Learning For Interactive Instruction Following Agents (2024, background): “…of incremental learning of novel tasks (Lesort et al., 2020) in various aspects including learning strategies ( e.g. , reinforcement learning (Khetarpal et al., 2018; Wołczyk et al., 2021; Xie & Finn, 2022), imitation learning (Mendez et al., 2018; Gao et al., 2021), etc. ) and task…”
• CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents (2021, background): “[26] discuss home simulations as a potentially suitable environment to benchmark continual RL.”