TRPO

Parameters

33.5K

Published

Feb 19, 2015

TRPO is an AI model developed by University of California (UC) Berkeley (United States), first published in February 2015. It works in the games domain, on tasks such as atari.

Epoch AI has no training-compute estimate for this model. The model has 33,500 parameters.

Access: Unreleased. Its weights are not openly released. The reference paper has 8,305 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: University of California (UC) Berkeley
Country of organization: United States
Domain: Games
Task: Atari
Parameters: 33,500
Training time: 30 h
Model accessibility: Unreleased
Open weights: No
Citations: 8,305
Epoch confidence: Confident

More from University of California (UC) Berkeley

Denoising Diffusion Probabilistic Models (LSUN Bedroom)Tensor-Transformer(1core)+PN (WT103)Humanoid Locomotion Starling-LM-7B-alpha GPT-2 (AMPS)SqueezeBERT CURL Tensor-Transformer(1core)+PN (PTB)

SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.

← All ai models