feat(mathy_alpha_sm): more stable recurrent model

 - trained on multiple poly/complex/binomial tasks

Author: justindujardin

libraries/mathy_alpha_sm/mathy_alpha_sm/model.config.json

@@ -1,57 +1,59 @@
 {
-  "name": "mathy_alpha_sm",
-  "version": "0.6.7",
-  "description": "Mathy.ai multi-task small model",
-  "license": "CC BY-SA 3.0",
-  "author": "Justin DuJardin",
-  "email": "justin@dujardinconsulting.com",
-  "url": "https://mathy.ai",
-  "mathy_version": ">=0.6.2,<1.0.0",
-  "prediction_window_size": 7,
-  "use_lstm": true,
-  "units": 512,
-  "embedding_units": 512,
-  "lstm_units": 128,
-  "topics": [
+  "name":"mathy_alpha_sm",
+  "version":"0.6.7",
+  "description":"Mathy.ai multi-task small model",
+  "license":"CC BY-SA 3.0",
+  "author":"Justin DuJardin",
+  "email":"justin@dujardinconsulting.com",
+  "url":"https://mathy.ai",
+  "mathy_version":">=0.6.7,<1.0.0",
+  "prediction_window_size":16,
+  "dropout":0.2,
+  "units":256,
+  "embedding_units":256,
+  "lstm_units":128,
+  "topics":[
     "poly",
+    "poly-combine",
     "complex",
-    "binomial"
+    "binomial",
+    "poly-blockers"
   ],
-  "difficulty": null,
-  "model_name": "model",
-  "init_model_from": null,
-  "train": false,
-  "verbose": true,
-  "lr": 0.001,
-  "max_eps": 5000,
-  "summary_interval": 100,
-  "gamma": 0.99,
-  "num_workers": 4,
-  "td_lambda": 0.2,
-  "print_training": false,
-  "print_model_call_times": false,
-  "print_mode": "terminal",
-  "normalization_style": "layer",
-  "use_term_order": false,
-  "use_tree_complexity": false,
-  "use_grouping_control": false,
-  "clip_grouping_control": true,
-  "use_env_features": true,
-  "use_node_values": true,
-  "update_gradients_every": 6,
-  "num_thinking_steps_begin": 3,
-  "mcts_sims": 10,
-  "worker_wait": 0.01,
-  "profile": false,
-  "action_strategy": "a3c",
-  "main_worker_use_epsilon": false,
-  "e_greedy_min": 0.01,
-  "e_greedy_max": 0.3,
-  "entropy_loss_scaling": 0.05,
-  "normalize_entropy_loss": true,
-  "aux_tasks_weight_scale": 0.1,
-  "teacher_start_evaluations_at_episode": 50,
-  "teacher_evaluation_steps": 5,
-  "teacher_promote_wins": 0.95,
-  "teacher_demote_wins": 0.6
+  "difficulty":null,
+  "model_dir":"mathy_alpha_sm",
+  "model_name":"model",
+  "init_model_from":null,
+  "train":false,
+  "verbose":true,
+  "lr_initial":0.01,
+  "lr_decay_steps":100,
+  "lr_decay_rate":0.96,
+  "lr_decay_staircase":true,
+  "max_eps":15000,
+  "summary_interval":100,
+  "gamma":0.99,
+  "num_workers":4,
+  "td_lambda":0.2,
+  "print_training":false,
+  "print_model_call_times":false,
+  "print_mode":"terminal",
+  "normalization_style":"layer",
+  "use_grouping_control":false,
+  "clip_grouping_control":true,
+  "update_gradients_every":8,
+  "mcts_sims":10,
+  "worker_wait":0.01,
+  "profile":false,
+  "action_strategy":"a3c",
+  "main_worker_use_epsilon":false,
+  "e_greedy_min":0.01,
+  "e_greedy_max":0.1,
+  "entropy_loss_scaling":0.05,
+  "normalize_entropy_loss":true,
+  "normalize_pi_loss":true,
+  "aux_tasks_weight_scale":1.0,
+  "teacher_start_evaluations_at_episode":50,
+  "teacher_evaluation_steps":20,
+  "teacher_promote_wins":0.95,
+  "teacher_demote_wins":0.5
 }