Browse SoTA > Methodology > Imitation Learning

Imitation Learning

131 papers with code ยท Methodology

Imitation Learning is a framework for learning a behavior policy from demonstrations. Usually, demonstrations are presented in the form of state-action trajectories, with each pair indicating the action to take at the state being visited. In order to learn the behavior policy, the demonstrated actions are usually utilized in two ways. The first, known as Behavior Cloning (BC), treats the action as the target label for each state, and then learns a generalized mapping from states to actions in a supervised manner. Another way, known as Inverse Reinforcement Learning (IRL), views the demonstrated actions as a sequence of decisions, and aims at finding a reward/cost function under which the demonstrated decisions are optimal.

Source: Adversarial Imitation Learning from Incomplete Demonstrations

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Latest papers without code

What is the Reward for Handwriting? -- Handwriting Generation by Imitation Learning

23 Sep 2020

In this study, we use a reinforcement learning (RL) framework to realize handwriting generation with the careful future planning ability.

IMITATION LEARNING

Addressing reward bias in Adversarial Imitation Learning with neutral reward functions

20 Sep 2020

Generative Adversarial Imitation Learning suffers from the fundamental problem of reward bias stemming from the choice of reward functions used in the algorithm.

IMITATION LEARNING

A Contraction Approach to Model-based Reinforcement Learning

18 Sep 2020

To this end, we analyze the error in cumulative reward for both stochastic and deterministic transitions using a contraction approach.

IMITATION LEARNING

Compressed imitation learning

18 Sep 2020

In analogy to compressed sensing, which allows sample-efficient signal reconstruction given prior knowledge of its sparsity in frequency domain, we propose to utilize policy simplicity (Occam's Razor) as a prior to enable sample-efficient imitation learning.

IMITATION LEARNING

Evolutionary Selective Imitation: Interpretable Agents by Imitation Learning Without a Demonstrator

17 Sep 2020

We propose a new method for training an agent via an evolutionary strategy (ES), in which we iteratively improve a set of samples to imitate: Starting with a random set, in every iteration we replace a subset of the samples with samples from the best trajectories discovered so far.

IMITATION LEARNING OPENAI GYM POLICY GRADIENT METHODS

Autoregressive Knowledge Distillation through Imitation Learning

15 Sep 2020

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures.

IMITATION LEARNING TEXT GENERATION

Toward the Fundamental Limits of Imitation Learning

13 Sep 2020

Here, we show that the policy which mimics the expert whenever possible is in expectation $\lesssim \frac{|\mathcal{S}| H^2 \log (N)}{N}$ suboptimal compared to the value of the expert, even when the expert follows an arbitrary stochastic policy.

DECISION MAKING IMITATION LEARNING

Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator

30 Aug 2020

Extensive experiments are conducted to demonstrate the accuracy of the proposed imitating learning process as well as the reliability of the holistic system for autonomous drone navigation.

DRONE NAVIGATION IMITATION LEARNING

Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles

28 Aug 2020

The simulation results shows that the proposed method achieves an overall success rate up to 20% higher than the benchmark model when it is generalized to the new environment of heavy traffic density.

AUTONOMOUS VEHICLES IMITATION LEARNING META REINFORCEMENT LEARNING

ADAIL: Adaptive Adversarial Imitation Learning

23 Aug 2020

We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single source domain.

IMITATION LEARNING