REVIEW 1 cited by
Multi-task Maximum Entropy Inverse Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Multi-task Maximum Entropy Inverse Reinforcement Learning
read the original abstract
Multi-task Inverse Reinforcement Learning (IRL) is the problem of inferring multiple reward functions from expert demonstrations. Prior work, built on Bayesian IRL, is unable to scale to complex environments due to computational constraints. This paper contributes a formulation of multi-task IRL in the more computationally efficient Maximum Causal Entropy (MCE) IRL framework. Experiments show our approach can perform one-shot imitation learning in a gridworld environment that single-task IRL algorithms need hundreds of demonstrations to solve. We outline preliminary work using meta-learning to extend our method to the function approximator setting of modern MCE IRL algorithms. Evaluating on multi-task variants of common simulated robotics benchmarks, we discover serious limitations of these IRL algorithms, and conclude with suggestions for further work.
Forward citations
Cited by 1 Pith paper
-
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
Learning the demonstrator's planning algorithm via a differentiable planner improves IRL reward inference over incorrect bias assumptions but underperforms exact planners.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.