search

uber-research / deep-neuroevolution

Deep Neuroevolution
Other
1.63k stars 301 forks source link

Local experiment run issue #19

Closed maomran closed 5 years ago

maomran commented 6 years ago

I lunch any of the local experiment after setting up redis server for master and relay. I get stuck in iteration 0 for the master while the relay keep retrying 2018-11-19 15:07:39,067 pid=31344] [master] Declared experiment {'config': {'calc_obstat_prob': 0.0, 'episode_cutoff_mode': 5000, 'episodes_per_batch': 5000, 'eval_prob': 0.01, 'l2coeff': 0.005, 'noise_stdev': 0.005, 'return_proc_mode': 'centered_rank', 'snapshot_freq': 20, 'timesteps_per_batch': 10000}, 'env_id': 'FrostbiteNoFrameskip-v4', 'num_elites': 1, 'policy': {'args': {'nonlin_type': 'relu'}, 'type': 'GAAtariPolicy'}, 'population_size': 10} ********** Iteration 0 ********** [2018-11-19 15:10:58,121 pid=31372] es:exp not set. Retrying after 4.89 sec (41/300) I am not sure why the workers cannot connect to the master.

VashishtMadhavan commented 5 years ago

Sorry for the late response, but I'm not able to reproduce your error. Try reducing your episodes_per_batch to 10 and timesteps_per_batch to 1000 and see if you are getting the same error.

maomran commented 5 years ago

No worries it was a redis-server version problem.

thisisjasleen commented 4 years ago

Hey, I am getting this same error.I don't think it is because of the redis server version problem. Did you find the solution?