hidden_dims = (256, 256, 256)
dropout_rate = 0.0
layer_norm = False
clip_grad_norm = 1.0
sampler = ddpm
ema_tau = 0.005
update_ema_every = 5
step_start_ema = 1000
use_guidance_loss = True
ddim_step = 5
clip_sampler = True
beta_schedule = vp
action_prior = normal
act_with_q_guid = False
action_argmax = True
logtostderr = False
alsologtostderr = False
log_dir = 
v = 0
verbosity = 0
logger_levels = {}
stderrthreshold = fatal
showprefixforinfo = True
chex_n_cpu_devices = 1
chex_assert_multiple_cpu_devices = False
run_with_pdb = False
pdb_post_mortem = False
pdb = False
run_with_profiling = False
profile_file = None
use_cprofile_for_profiling = True
only_check_args = False
test_srcdir = 
test_tmpdir = /tmp/absl_testing
test_random_seed = 301
test_randomize_ordering_seed = 
xml_output_file = 
chex_skip_pmap_variant_if_single_device = True
op_conversion_fallback_to_while_loop = True
delta_threshold = 0.5
tt_check_filter = False
tt_single_core_summaries = False
runtime_oom_exit = True
hbm_oom_exit = True
env = walker2d-medium-v2
reward_tune = iql_locomotion
dataset_name = d4rl
agent = dac
seed = 0
num_seed_runs = 8
n_eval_episodes = 10
log_interval = 5000
eval_interval = 10000
batch_size = 256
max_steps = 2000000
finetune_step = 3000000
buffer_size = 1000000
discount = 0.99
percentile = 100.0
percentage = 100.0
tqdm = True
save_video = False
save_ckpt = False
test = False
tag = sota
T = 5
eta = 1.0
eta_min = 0.001
eta_max = 100.0
eta_lr = 0.001
rho = 1.0
bc_threshold = 1.0
actor_lr = 0.0003
critic_lr = 0.0003
q_tar = lcb
maxQ = False
resnet = False
num_qs = 10
num_q_samples = 10
num_action_samples = 10
? = False
help = False
helpshort = False
helpfull = False
helpxml = False
Save_folder = results/walker2d-medium-v2/DAC_b=1.0|QTar=lcb|rho=1.0
