From bf0a386b5354a2852b806e1f7b5b8a37992630fb Mon Sep 17 00:00:00 2001 From: Aakash Kumar Date: Sat, 9 May 2020 11:46:36 +0530 Subject: [PATCH 1/2] changing argument according to updated gym --- README.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 2ae5bba..c3a1393 100644 --- a/README.md +++ b/README.md @@ -21,14 +21,15 @@ A basic script for training a Deep-Q agent: def main(): env = gym.make("balancebot-v0") - model = deepq.models.mlp([16, 12]) + # model = deepq.models.mlp([16, 12]) act = deepq.learn( env, - q_func=model, + network=model, lr=1e-3, - max_timesteps=100000, - buffer_size=100000, - exploration_fraction=0.1, + max_timesteps='mlp', + total_timesteps=100000, + buffer_size = 5000, + exploration_fraction=0.5, exploration_final_eps=0.02, print_freq=10, callback=callback From f95ca54d03e0603a56093342caca3624b0f85f13 Mon Sep 17 00:00:00 2001 From: Aakash Kumar Date: Sat, 9 May 2020 11:48:59 +0530 Subject: [PATCH 2/2] adjusting parameters after removal of deepq.models.mlp --- README.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index c3a1393..57f8b81 100644 --- a/README.md +++ b/README.md @@ -24,11 +24,10 @@ A basic script for training a Deep-Q agent: # model = deepq.models.mlp([16, 12]) act = deepq.learn( env, - network=model, + network='mlp', lr=1e-3, - max_timesteps='mlp', - total_timesteps=100000, - buffer_size = 5000, + total_timesteps=200000, + buffer_size = 50000, exploration_fraction=0.5, exploration_final_eps=0.02, print_freq=10,