satcos
/

DT-BipedalWalker-v3

Reinforcement Learning Transformers Safetensors decision_transformer BipedalWalker-v3 reinforce custom-implementation deep-rl-class Eval Results Inference Endpoints

Model card Files Files and versions Community

Edit model card

Reinforce Agent playing BipedalWalker-v3

This is a trained model of a Reinforce agent playing BipedalWalker-v3 .

Downloads last month: 4

Safetensors

Model size

1.26M params

Tensor type

F32

·

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on BipedalWalker-v3
self-reported

196.20 +/- 4.38

View on Papers With Code