Quentin Gallouédec
Initial commit
a32d6cd
raw
history blame
440 Bytes
!!python/object/apply:collections.OrderedDict
- - - batch_size
- 128
- - cg_damping
- 0.1
- - cg_max_steps
- 25
- - gae_lambda
- 0.95
- - gamma
- 0.99
- - learning_rate
- 0.001
- - n_critic_updates
- 20
- - n_envs
- 2
- - n_steps
- 1024
- - n_timesteps
- 1000000.0
- - normalize
- true
- - policy
- MlpPolicy
- - sub_sampling_factor
- 1
- - target_kl
- 0.04