Imitation Learning

509 papers with code • 0 benchmarks • 18 datasets

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.

Finally, a newer methodology, Inverse Q-Learning aims at directly learning Q-functions from expert data, implicitly representing rewards, under which the optimal policy can be given as a Boltzmann distribution similar to soft Q-learning

Source: Learning to Imitate

Libraries

Use these libraries to find Imitation Learning models and implementations

LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation

kguo-cs/lsail 26 Mar 2024

Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations.

2
26 Mar 2024

Rethinking Adversarial Inverse Reinforcement Learning: From the Angles of Policy Imitation and Transferable Reward Recovery

garyzyr001/rethinking-airl 21 Mar 2024

Adversarial inverse reinforcement learning (AIRL) stands as a cornerstone approach in imitation learning.

1
21 Mar 2024

3D Diffusion Policy

YanjieZe/3D-Diffusion-Policy 6 Mar 2024

Imitation learning provides an efficient way to teach robots dexterous skills; however, learning complex skills robustly and generalizablely usually consumes large amounts of human demonstrations.

132
06 Mar 2024

Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking

nathangavenski/il-datasets 1 Mar 2024

Imitation learning field requires expert data to train agents in a task.

4
01 Mar 2024

HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding

kaist-silab/himap 23 Feb 2024

With a simple training scheme and implementation, HiMAP demonstrates competitive results in terms of success rate and scalability in the field of imitation-learning-only MAPF, showing the potential of imitation-learning-only MAPF equipped with inference techniques.

2
23 Feb 2024

Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions

lucascjysdl/dgms-for-offline-policy-learning 21 Feb 2024

This work offers a hands-on reference for the research progress in deep generative models for offline policy learning, and aims to inspire improved DGM-based offline RL or IL algorithms.

8
21 Feb 2024

Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers

dagabo98/dt-quadruped-locomotion 20 Feb 2024

Our results show that quantization (down to 4 bits) and pruning reduce model size by around 30\% while maintaining a competitive reward, making the model deployable in a resource-constrained system.

0
20 Feb 2024

PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem

frankzheng2022/prise 16 Feb 2024

To do so, we bring a subtle but critical component of LLM training pipelines -- input tokenization via byte pair encoding (BPE) -- to the seemingly distant task of learning skills of variable time span in continuous control domains.

6
16 Feb 2024

Hybrid Inverse Reinforcement Learning

jren03/garage 13 Feb 2024

In this work, we propose using hybrid RL -- training on a mixture of online and expert data -- to curtail unnecessary exploration.

2
13 Feb 2024

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

premiertaco/premier-taco 9 Feb 2024

We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks.

4
09 Feb 2024