Merge

Author: Joseph Suarez

pufferlib/config/ocean/asteroids.ini

@@ -12,5 +12,26 @@ num_envs = 1024
 size = 500
 
 [train]
-total_timesteps = 150_000_000
-minibatch_size = 32768
+adam_beta1 = 0.975493290069733
+adam_beta2 = 0.9999436458974764
+adam_eps = 6.915036275112011e-08
+anneal_lr = true
+batch_size = auto
+bptt_horizon = 64
+checkpoint_interval = 200
+clip_coef = 0.18588778503512546
+ent_coef = 0.0016620361911332262
+gae_lambda = 0.8400278040617952
+gamma = 0.9998708818940873
+learning_rate = 0.00502237062536979
+max_grad_norm = 0.7306435358436453
+max_minibatch_size = 32768
+minibatch_size = 8192
+prio_alpha = 0.9165093859993415
+prio_beta0 = 0.8869674411376214
+total_timesteps = 100_000_000
+update_epochs = 1
+vf_clip_coef = 0.1
+vf_coef = 2.960148388519086
+vtrace_c_clip = 1.0767718761515104
+vtrace_rho_clip = 4.132507367126342

pufferlib/config/ocean/g2048.ini

@@ -4,9 +4,36 @@ env_name = puffer_g2048
 policy_name = G2048
 rnn_name = Recurrent
 
+[policy]
+hidden_size = 256
+
+[rnn]
+input_size = 256
+hidden_size = 256
+
+[vec]
+num_envs = 4
+
 [env]
-num_envs = 4096
+num_envs = 4024
 
 [train]
-total_timesteps = 1_000_000_000
-minibatch_size = 32768
+total_timesteps = 600_000_000
+adam_beta1 = 0.9529488439604378
+adam_beta2 = 0.9993901829477296
+adam_eps = 2.745365927413118e-7
+bptt_horizon = 64
+clip_coef = 0.596573170393339
+ent_coef = 0.02107417730003862
+gae_lambda = 0.9940613415815854
+gamma = 0.9889857974154952
+learning_rate = 0.0032402460796988127
+max_grad_norm = 1.0752406726589745
+minibatch_size = 16384
+prio_alpha = 0.25297099593586336
+prio_beta0 = 0.940606268942572
+vf_clip_coef = 0.1
+vf_coef = 1.6362878279900643
+vtrace_c_clip = 0
+vtrace_rho_clip = 1.2917509971869054
+anneal_lr = False