From a4d81d3205fc14e5b0a42c24a1c2666110c98982 Mon Sep 17 00:00:00 2001 From: Andrew Cohen Date: Wed, 17 Jun 2020 12:40:42 -0700 Subject: [PATCH 1/3] update config 3dball --- config/ppo/3DBallHard.yaml | 4 ++-- config/sac/3DBall.yaml | 4 ++-- config/sac/3DBallHard.yaml | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/config/ppo/3DBallHard.yaml b/config/ppo/3DBallHard.yaml index 6dc83100f2..c8a1ae74d0 100644 --- a/config/ppo/3DBallHard.yaml +++ b/config/ppo/3DBallHard.yaml @@ -5,7 +5,7 @@ behaviors: batch_size: 1200 buffer_size: 12000 learning_rate: 0.0003 - beta: 0.001 + beta: 0.0001 epsilon: 0.2 lambd: 0.95 num_epoch: 3 @@ -20,7 +20,7 @@ behaviors: gamma: 0.995 strength: 1.0 keep_checkpoints: 5 - max_steps: 5000000 + max_steps: 2000000 time_horizon: 1000 summary_freq: 12000 threaded: true diff --git a/config/sac/3DBall.yaml b/config/sac/3DBall.yaml index 0458c03070..e6f91bc548 100644 --- a/config/sac/3DBall.yaml +++ b/config/sac/3DBall.yaml @@ -5,7 +5,7 @@ behaviors: learning_rate: 0.0003 learning_rate_schedule: constant batch_size: 64 - buffer_size: 12000 + buffer_size: 200000 buffer_init_steps: 0 tau: 0.005 steps_per_update: 10.0 @@ -22,7 +22,7 @@ behaviors: gamma: 0.99 strength: 1.0 keep_checkpoints: 5 - max_steps: 500000 + max_steps: 200000 time_horizon: 1000 summary_freq: 12000 threaded: true diff --git a/config/sac/3DBallHard.yaml b/config/sac/3DBallHard.yaml index 511f375bc2..e34bb93a79 100644 --- a/config/sac/3DBallHard.yaml +++ b/config/sac/3DBallHard.yaml @@ -5,7 +5,7 @@ behaviors: learning_rate: 0.0003 learning_rate_schedule: constant batch_size: 256 - buffer_size: 50000 + buffer_size: 500000 buffer_init_steps: 0 tau: 0.005 steps_per_update: 10.0 From e5bba80de5ba1c20fa64a2972335cb9a3aedf54f Mon Sep 17 00:00:00 2001 From: Andrew Cohen Date: Wed, 17 Jun 2020 13:38:57 -0700 Subject: [PATCH 2/3] zeroing out beta ppo 3dballhard --- config/ppo/3DBallHard.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/config/ppo/3DBallHard.yaml b/config/ppo/3DBallHard.yaml index c8a1ae74d0..c936c4cf84 100644 --- a/config/ppo/3DBallHard.yaml +++ b/config/ppo/3DBallHard.yaml @@ -5,7 +5,7 @@ behaviors: batch_size: 1200 buffer_size: 12000 learning_rate: 0.0003 - beta: 0.0001 + beta: 0.0 epsilon: 0.2 lambd: 0.95 num_epoch: 3 From 9bbe2c998b0b06d96341efdce6e5cbb3b938968f Mon Sep 17 00:00:00 2001 From: Andrew Cohen Date: Wed, 17 Jun 2020 14:51:35 -0700 Subject: [PATCH 3/3] revert ppo 3dball hard to master --- config/ppo/3DBallHard.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/config/ppo/3DBallHard.yaml b/config/ppo/3DBallHard.yaml index c936c4cf84..6dc83100f2 100644 --- a/config/ppo/3DBallHard.yaml +++ b/config/ppo/3DBallHard.yaml @@ -5,7 +5,7 @@ behaviors: batch_size: 1200 buffer_size: 12000 learning_rate: 0.0003 - beta: 0.0 + beta: 0.001 epsilon: 0.2 lambd: 0.95 num_epoch: 3 @@ -20,7 +20,7 @@ behaviors: gamma: 0.995 strength: 1.0 keep_checkpoints: 5 - max_steps: 2000000 + max_steps: 5000000 time_horizon: 1000 summary_freq: 12000 threaded: true