search

cogment / cogment-verse

Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)
https://cogment.ai/cogment_verse
Apache License 2.0
76 stars 14 forks source link

TD3 #94

Closed saikrishna-1996 closed 1 year ago

saikrishna-1996 commented 1 year ago

ToDo: sample random action for first 25000 time steps. We need a working sample_space function (for continuous actions) for that.

cloderic commented 1 year ago

Add a little readme on the algorithm + some training traces (basics of a model card)