decision-transformer-halfcheetah-v4

This model was trained from scratch on the halfcheetah-expert-v2 dataset. For full code see: https://www.kaggle.com/code/syedjarullahhisham/drl-adv-hf-decisiontransformer-halfcheetah-hopper

Codes

Github repos(Give a star if found useful):

• https://github.com/hishamcse/DRL-Renegades-Game-Bots
• https://github.com/hishamcse/Advanced-DRL-Renegades-Game-Bots
• https://github.com/hishamcse/Robo-Chess

Kaggle Notebook:

• https://www.kaggle.com/code/syedjarullahhisham/drl-adv-hf-decisiontransformer-halfcheetah-hopper

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 128
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 240

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1