contrastive_unsupervised_rl¶

curl_learner¶

class xuance.mindspore.learners.contrastive_unsupervised_rl.curl_learner.CURL_Learner(config: Namespace, policy: torch.nn.Module, callback)[source]¶

Bases: Learner

update(**samples)[source]¶

class xuance.mindspore.learners.contrastive_unsupervised_rl.curl_learner.FrameStackTransform[source]¶: Bases: object

drq_learner¶

Deep Q-Network (DQN) Paper link: https://www.nature.com/articles/nature14236 Implementation: Pytorch

class xuance.mindspore.learners.contrastive_unsupervised_rl.drq_learner.DrQ_Learner(config: Namespace, policy: torch.nn.Module)[source]¶

Bases: Learner

update(**samples)[source]¶

class xuance.mindspore.learners.contrastive_unsupervised_rl.drq_learner.FrameStackTransform[source]¶: Bases: object

spr_learner¶

class xuance.mindspore.learners.contrastive_unsupervised_rl.spr_learner.FrameStackTransform[source]¶: Bases: object

class xuance.mindspore.learners.contrastive_unsupervised_rl.spr_learner.SPR_Learner(config, policy, callback, temperature=0.1, tau=0.99, repr_lr=0.0001, prediction_steps=3)[source]¶

Bases: Learner

update(**samples)[source]¶