Decision Transformer model trained on medium-replay trajectories sampled from the Gym Hopper environment

This is a trained Decision Transformer model trained on medium-replay trajectories sampled from the Gym Hopper environment.

The following normlization coefficients are required to use this model:

mean = [ 1.2305138, -0.04371411, -0.44542956, -0.09370098, 0.09094488, 1.3694725, -0.19992675, -0.02286135, -0.5287045, -0.14465883, -0.19652697]

std = [0.17565121, 0.06369286, 0.34383234, 0.19566889, 0.5547985, 1.0510299, 1.1583077, 0.79631287, 1.4802359, 1.6540332, 5.108601]

See our Blog Post, Colab notebook or Example Script for usage.

Downloads last month
13
Video Preview
loading

Model tree for edbeeching/decision-transformer-gym-hopper-medium-replay

Quantizations
1 model