The reviewed record of science sign in
Pith

arxiv: 2110.02414 · v2 · pith:JMV2FC4B · submitted 2021-10-05 · cs.LG · cs.RO

Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks

Reviewed by Pithpith:JMV2FC4Bopen to challenge →

classification cs.LG cs.RO
keywords model-basedexperiencehindsightimaginarylearningreplayrewardtasks
0
0 comments X
read the original abstract

Model-based reinforcement learning is a promising learning strategy for practical robotic applications due to its improved data-efficiency versus model-free counterparts. However, current state-of-the-art model-based methods rely on shaped reward signals, which can be difficult to design and implement. To remedy this, we propose a simple model-based method tailored for sparse-reward multi-goal tasks that foregoes the need for complicated reward engineering. This approach, termed Imaginary Hindsight Experience Replay, minimises real-world interactions by incorporating imaginary data into policy updates. To improve exploration in the sparse-reward setting, the policy is trained with standard Hindsight Experience Replay and endowed with curiosity-based intrinsic rewards. Upon evaluation, this approach provides an order of magnitude increase in data-efficiency on average versus the state-of-the-art model-free method in the benchmark OpenAI Gym Fetch Robotics tasks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.