DeepAI AI Chat
Log In Sign Up

MANGA: Method Agnostic Neural-policy Generalization and Adaptation

11/19/2019
by   Homanga Bharadhwaj, et al.
UNIVERSITY OF TORONTO
23

In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environment with changes in dynamics configurations in the presence of motor noise is very important for operating robots in the real world, and our work is a novel attempt in that direction. We introduce MANGA: Method Agnostic Neural-policy Generalization and Adaptation, that trains dynamics conditioned policies and efficiently learns to estimate the dynamics parameters of the environment given off-policy state-transition rollouts in the environment. Our scheme is agnostic to the type of training method used - both reinforcement learning (RL) and imitation learning (IL) strategies can be used. We demonstrate the effectiveness of our approach by experimenting with four different MuJoCo agents and comparing against previously proposed transfer baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8

03/04/2019

NoRML: No-Reward Meta Learning

Efficiently adapting to new environments and changes in dynamics is crit...
03/12/2021

Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

Domain adaptation is a common problem in robotics, with applications suc...
10/06/2021

Nested Policy Reinforcement Learning

Off-policy reinforcement learning (RL) has proven to be a powerful frame...
07/26/2019

Environment Probing Interaction Policies

A key challenge in reinforcement learning (RL) is environment generaliza...
03/08/2023

Learning Exploration Strategies to Solve Real-World Marble Runs

Tasks involving locally unstable or discontinuous dynamics (such as bifu...
10/18/2019

RTFM: Generalising to Novel Environment Dynamics via Reading

Obtaining policies that can generalise to new environments in reinforcem...
10/07/2019

Force Field Generalization and the Internal Representation of Motor Learning

When learning a new motor behavior, e.g. reaching in a force field, the ...