LTU-AI
/

hdppo-Acrobot-v1

Reinforcement Learning

deep-reinforcement-learning

hyperdimensional-computing

fractional-power-encoding

Eval Results (legacy)

Model card Files Files and versions

hdppo-Acrobot-v1 / config.yml

ChirathD's picture

Add hdppo-Acrobot-v1 package (weights, code, model card)

12f4526 verified 8 days ago

History Blame Contribute Delete

244 Bytes

	!!python/object/apply:collections.OrderedDict
	-
	- - env
	- Acrobot-v1
	- - algo
	- HD-PPO (gradient-adaptive FPE, discrete)
	- - teacher_D
	- 256
	- - pruned_D
	- 16
	- - timesteps_per_stage
	- 1000000
	- - seed
	- 123