The Pitfalls of Imitation Learning when Actions are Continuous
We study the problem of imitating an expert demonstrator in a discrete-time, continuous state-and-action control system. We show that, even if the dynamics satisfy a control-theoretic property called exponentially stability (i.e. the effects of perturbations decay exponentially quickly), and the expert is smooth and deterministic, any smooth, deterministic imitator policy necessarily suffers error on execution that is exponentially larger, as a function of problem horizon, than the error under the distribution of expert training data. Our negative result applies to any algorithm which learns solely from expert data, including both behavior cloning and offline-RL algorithms, unless the algorithm produces highly "improper" imitator policies--those which are non-smooth, non-Markovian, or which exhibit highly state-dependent stochasticity--or unless the expert trajectory distribution is sufficiently "spread." We provide experimental evidence of the benefits of these more complex policy parameterizations, explicating the benefits of today's popular policy parameterizations in robot learning (e.g. action-chunking and Diffusion Policies). We also establish a host of complementary negative and positive results for imitation in control systems.
Code (0)
등록된 구현이 없습니다.
Tasks
ChunkingImitation LearningOffline RLMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms
We formulate the problem of learning to imitate multiple, non-deterministic teachers with minimal interaction cost. Rather than learning a specific policy as in standard imitation learning, the goal in this problem is to…
Active LearningImitation LearningNine Potential Pitfalls when Designing Human-AI Co-Creative Systems
This position paper examines potential pitfalls on the way towards achieving human-AI co-creation with generative models in a way that is beneficial to the users' interests. In particular, we collected a set of nine pote…
PositionIce Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference
Reliable causal inference is essential for making decisions in high-stakes areas like medicine, economics, and public policy. However, it remains unclear whether large language models (LLMs) can handle rigorous and trust…
BenchmarkingCausal InferenceSelection biasPitfalls in the Evaluation of Sentence Embeddings
Deep learning models continuously break new records across different NLP tasks. At the same time, their success exposes weaknesses of model evaluation. Here, we compile several key pitfalls of evaluation of sentence embe…
SentenceSentence EmbeddingsGeneral Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models
An increasing number of model-agnostic interpretation techniques for machine learning (ML) models such as partial dependence plots (PDP), permutation feature importance (PFI) and Shapley values provide insightful model i…
BIG-bench Machine LearningFeature Importance