◆ action_repeat
| int rl_stl.policies.ppo_checkpoint.PPOConfig.action_repeat = 1 |
|
static |
◆ batch_size
| int rl_stl.policies.ppo_checkpoint.PPOConfig.batch_size = 64 |
|
static |
◆ clipping_epsilon
| float rl_stl.policies.ppo_checkpoint.PPOConfig.clipping_epsilon = 0.2 |
|
static |
◆ discounting
| float rl_stl.policies.ppo_checkpoint.PPOConfig.discounting = 0.99 |
|
static |
◆ entropy_cost
| float rl_stl.policies.ppo_checkpoint.PPOConfig.entropy_cost = 1e-3 |
|
static |
◆ episode_length
| int rl_stl.policies.ppo_checkpoint.PPOConfig.episode_length = 200 |
|
static |
◆ learning_rate
| float rl_stl.policies.ppo_checkpoint.PPOConfig.learning_rate = 3e-4 |
|
static |
◆ max_grad_norm
| float rl_stl.policies.ppo_checkpoint.PPOConfig.max_grad_norm = 1.0 |
|
static |
◆ normalize_observations
| bool rl_stl.policies.ppo_checkpoint.PPOConfig.normalize_observations = True |
|
static |
◆ num_envs
| int rl_stl.policies.ppo_checkpoint.PPOConfig.num_envs = 64 |
|
static |
◆ num_eval_envs
| int rl_stl.policies.ppo_checkpoint.PPOConfig.num_eval_envs = 64 |
|
static |
◆ num_evals
| int rl_stl.policies.ppo_checkpoint.PPOConfig.num_evals = 3 |
|
static |
◆ num_minibatches
| int rl_stl.policies.ppo_checkpoint.PPOConfig.num_minibatches = 4 |
|
static |
◆ num_resets_per_eval
| int rl_stl.policies.ppo_checkpoint.PPOConfig.num_resets_per_eval = 0 |
|
static |
◆ num_timesteps
| int rl_stl.policies.ppo_checkpoint.PPOConfig.num_timesteps = 50_000 |
|
static |
◆ num_updates_per_batch
| int rl_stl.policies.ppo_checkpoint.PPOConfig.num_updates_per_batch = 2 |
|
static |
◆ reward_scaling
| float rl_stl.policies.ppo_checkpoint.PPOConfig.reward_scaling = 1.0 |
|
static |
◆ unroll_length
| int rl_stl.policies.ppo_checkpoint.PPOConfig.unroll_length = 10 |
|
static |
The documentation for this class was generated from the following file: