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
Benchmarks
These leaderboards are used to track progress in Imitation Learning
Libraries
Use these libraries to find Imitation Learning models and implementationsDatasets
Latest papers
LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation
Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations.
Rethinking Adversarial Inverse Reinforcement Learning: From the Angles of Policy Imitation and Transferable Reward Recovery
Adversarial inverse reinforcement learning (AIRL) stands as a cornerstone approach in imitation learning.
3D Diffusion Policy
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.
Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking
Imitation learning field requires expert data to train agents in a task.
HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding
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.
Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions
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.
Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers
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.
PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem
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.
Hybrid Inverse Reinforcement Learning
In this work, we propose using hybrid RL -- training on a mixture of online and expert data -- to curtail unnecessary exploration.
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks.