action_repeat: 4
actor_critic_batch_size: 64
actor_critic_steps_per_epoch: 50
actor_hidden_size: 512
actor_layers: 1
actor_learning_rate: 0.0001
adam_beta1: 0.9
adam_beta2: 0.999
atari_100k: true
autoencoder_batch_size: 64
burn_in_length: 20
checkpoint_interval: 50
collect_epsilon: 0.01
collect_temperature: 1.0
collection_epochs: 500
commitment_weight: 1.0
decoder_depth: 64
discount: 0.995
early_stopping: false
encoder_channels: 64
encoder_layers: 4
encoder_residual_blocks: 2
entropy_coef: 0.001
env: ALE/Pong-v5
env_backend: gym
env_steps_per_epoch: 200
eval_episodes: 100
eval_temperature: 0.5
frame_channels: 3
frame_height: 64
frame_width: 64
grad_clip_norm: 10.0
gradient_checkpointing: true
imagination_horizon: 20
log_interval: 1000
max_env_steps: 100000
max_episode_steps: 27000
min_delta: 0.0001
model_learning_rate: 0.0001
patience: 10
perceptual_blocks: 5
perceptual_linear_weights: ''
perceptual_weight: 1.0
quantizer: gradient
reconstruction_weight: 1.0
repeat_action_probability: 0.0
reward_loss: cross_entropy
reward_transform: sign
start_actor_critic_after: 50
start_autoencoder_after: 5
start_transformer_after: 25
td_lambda: 0.95
token_embedding_dim: 512
tokens_per_frame: 16
total_epochs: 600
training_steps_per_epoch: 200
transformer_batch_size: 16
transformer_dropout: 0.1
transformer_embed_dim: 256
transformer_heads: 4
transformer_layers: 10
transformer_steps_per_epoch: 200
transformer_timesteps: 20
use_amp: true
value_learning_rate: 0.0001
vocab_size: 512
weight_decay: 0.01