diff --git a/isaac_sim/checkpoints/m20/exported/policy.pt b/isaac_sim/checkpoints/m20/exported/policy.pt index 5d6316d..710f567 100644 Binary files a/isaac_sim/checkpoints/m20/exported/policy.pt and b/isaac_sim/checkpoints/m20/exported/policy.pt differ diff --git a/isaac_sim/checkpoints/m20/params/agent.yaml b/isaac_sim/checkpoints/m20/params/agent.yaml index b622812..7ceeb40 100644 --- a/isaac_sim/checkpoints/m20/params/agent.yaml +++ b/isaac_sim/checkpoints/m20/params/agent.yaml @@ -7,13 +7,13 @@ obs_groups: {} clip_actions: 100 check_for_nan: true save_interval: 100 -experiment_name: deeprobotics_m20_spinlearn3 +experiment_name: deeprobotics_m20_spinlearn5 run_name: '' logger: tensorboard neptune_project: isaaclab wandb_project: isaaclab resume: true -load_run: 2026-07-19_04-05-44 +load_run: 2026-07-27_14-54-11 load_checkpoint: model_10998.pt class_name: OnPolicyRunner actor: diff --git a/isaac_sim/checkpoints/m20/params/env.yaml b/isaac_sim/checkpoints/m20/params/env.yaml index 660573f..dde0d02 100644 --- a/isaac_sim/checkpoints/m20/params/env.yaml +++ b/isaac_sim/checkpoints/m20/params/env.yaml @@ -1438,7 +1438,7 @@ rewards: - null - null preserve_order: false - target_height: 0.4 + target_height: 0.52 weight: -0.5 body_lin_acc_l2: null joint_torques_l2: @@ -2032,6 +2032,34 @@ rewards: params: command_name: base_velocity weight: 0.0 + joint_deviation_hipy_l1: + func: isaaclab.envs.mdp.rewards:joint_deviation_l1 + params: + asset_cfg: + name: robot + joint_names: + - .*_hipy_joint + joint_ids: !!python/object/apply:builtins.slice + - null + - null + - null + fixed_tendon_names: null + fixed_tendon_ids: !!python/object/apply:builtins.slice + - null + - null + - null + body_names: null + body_ids: !!python/object/apply:builtins.slice + - null + - null + - null + object_collection_names: null + object_collection_ids: !!python/object/apply:builtins.slice + - null + - null + - null + preserve_order: false + weight: -0.25 terminations: time_out: func: isaaclab.envs.mdp.terminations:time_out