Views
No views yet
*_pa_5 and *_pa_1 to see runs with previous action (the previous action dimension is 5 for null, up, left, right down) and without previous action (the previous action dimension is 1 for null).config.cfg for hyperparams, most are shared, the main difference is choice of alpha, discount_rate and num_prev_action, which as a result of this experiment now defaults to 1.num_prev_actions=?
discount_rate=?
alpha=?
seed=?al_{alpha}_g_{discoutn_rate}_seed_{seed}_pa_{num_prev_actions}rl_action=train
num_rollout_steps=64
lr=5e-05
eff_horizon=None
eval_every=1
use_wandb=True
use_hf=True
use_log=True
num_total_env_steps=5000000000
checkpoint=al_0.47_g_0.95_seed_105_pa_1
render_sixel=False
sixel_idx=60
seed=105
mask_type=first_episode
penalize_time=False
optim=adam
live_monitor=False
use_bf16=False
deterministic=True
eval_schedule=0:1,250:2,500:5,1000:10,2000:20
grad_acc_per_chunk=5
num_rollout_chunks=1
cheese_loc=any
env_layout=open
env_size=13
num_levels=9600
f_str_ckpt=al_{alpha}_g_{discount_rate}_seed_{seed}_pa_{num_prev_actions}
wandb_project=jaxgmg2_3phase_seed
ckpt_dir=jaxgmg2_3phase_seed
duplication_factor=-1
smoke=False
compile=True
num_chains=6
num_draws=3000
num_steps_bw_draws=1
on_policy=True
llc_nbeta=3000
localization=10
exact_solver_each_draw=False
llc_optimizer=sgld
iw_clip_eps=None
rmsprop_burnin_steps=20
llc_data_file=llc_scan_open_reinforce.pkl
llc_checkpoint_index=None
llc_checkpoint_number=None
sink=None
repo_id=davidquarel/jaxgmg_ckpt_zip
use_shuffled_checkpoints=False
force_re_download=False
off_distribution_data=False
weight_restrictions=None
weight_restrictions_invert=False
evaluate_every_position=False
use_prev_action=False
ntfy=david_jaxgmg