Merge pull request #61 from beduffy/master

Renamed args.tau to args.gae_lambda

Author: ikostrikov2

main.py

@@ -20,8 +20,8 @@
                     help='learning rate (default: 0.0001)')
 parser.add_argument('--gamma', type=float, default=0.99,
                     help='discount factor for rewards (default: 0.99)')
-parser.add_argument('--tau', type=float, default=1.00,
-                    help='parameter for GAE (default: 1.00)')
+parser.add_argument('--gae-lambda', type=float, default=1.00,
+                    help='lambda parameter for GAE (default: 1.00)')
 parser.add_argument('--entropy-coef', type=float, default=0.01,
                     help='entropy term coefficient (default: 0.01)')
 parser.add_argument('--value-loss-coef', type=float, default=0.5,

train.py

@@ -92,10 +92,10 @@ def train(rank, args, shared_model, counter, lock, optimizer=None):
             advantage = R - values[i]
             value_loss = value_loss + 0.5 * advantage.pow(2)
 
-            # Generalized Advantage Estimataion
+            # Generalized Advantage Estimation
             delta_t = rewards[i] + args.gamma * \
                 values[i + 1] - values[i]
-            gae = gae * args.gamma * args.tau + delta_t
+            gae = gae * args.gamma * args.gae_lambda + delta_t
 
             policy_loss = policy_loss - \
                 log_probs[i] * gae.detach() - args.entropy_coef * entropies[i]