Curiosity-Driven Multi-Criteria Hindsight Experience Replay

by   John B. Lanier, et al.
University of California, Irvine

Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the prediction error of a learned dynamics model as an intrinsic reward has been shown to be effective for exploring a number of sparse-reward environments. We present a method that combines hindsight with curiosity-driven exploration and curriculum learning in order to solve the challenging sparse-reward block stacking task. We are the first to stack more than two blocks using only sparse reward without human demonstrations.


Overcoming Exploration in Reinforcement Learning with Demonstrations

Exploration in environments with sparse rewards has been a persistent pr...

Fixed β-VAE Encoding for Curious Exploration in Complex 3D Environments

Curiosity is a general method for augmenting an environment reward with ...

Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning

Learning robotic manipulation tasks using reinforcement learning with sp...

Touch-based Curiosity for Sparse-Reward Tasks

Robots in many real-world settings have access to force/torque sensors i...

Hierarchical reinforcement learning for efficient exploration and transfer

Sparse-reward domains are challenging for reinforcement learning algorit...

Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning

We seek to efficiently learn by leveraging shared structure between diff...

BYOL-Explore: Exploration by Bootstrapped Prediction

We present BYOL-Explore, a conceptually simple yet general approach for ...

Please sign up or login with your details

Forgot password? Click here to reset