Behavioural cloning
8 papers with code • 0 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Behavioural cloning
BDD-X
CoWeSe
Most implemented papers
Counter-Strike Deathmatch with Large-Scale Behavioural Cloning
TeaPearce/Counter-Strike_Behavioural_Cloning
•
•
This paper describes an AI agent that plays the popular first-person-shooter (FPS) video game `Counter-Strike; Global Offensive' (CSGO) from pixel input.
A Divergence Minimization Perspective on Imitation Learning Methods
We present $f$-MAX, an $f$-divergence generalization of AIRL [Fu et al., 2018], a state-of-the-art IRL method.
Action Advising with Advice Imitation in Deep Reinforcement Learning
ercumentilhan/naive-advice-imitation
•
•
Action advising is a peer-to-peer knowledge exchange technique built on the teacher-student paradigm to alleviate the sample inefficiency problem in deep reinforcement learning.
Deep attention networks reveal the rules of collective motion in zebrafish
When using simulated trajectories, the model recovers the ground-truth interaction rule used to generate them, as well as the number of interacting neighbours.
Benchmarking End-to-End Behavioural Cloning on Video Games
joonaspu/video-game-behavioural-cloning
•
•
We take a step towards a general approach and study the general applicability of behavioural cloning on twelve video games, including six modern video games (published after 2010), by using human demonstrations as training data.
Playing Minecraft with Behavioural Cloning
MineRL 2019 competition challenged participants to train sample-efficient agents to play Minecraft, by using a dataset of human gameplay and a limit number of steps the environment.
Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning
alexbeesonwarwick/offlinerlconstrainedensemble
•
•
Offline reinforcement learning agents seek optimal policies from fixed data sets.
Self-Supervised Adversarial Imitation Learning
We address this limitation by incorporating a discriminator into the original framework, offering two key advantages and directly solving a learning problem previous work had.
