├── core ├── agent.py ├── agent_noniid.py ├── agent_ray.py ├── agent_ray_gpu.py ├── agent_ray_pd.py ├── common.py ├── common_ray.py ├── common_ray_gpu.py ├── common_ray_navi.py ├── log_determinant.py ├── log_determinant_hessian.py ├── log_determinant_hessian_ray.py ├── log_determinant_ray.py ├── models.py ├── natural_gradient.py ├── natural_gradient_ray.py ├── natural_gradient_ray_gpu.py ├── natural_gradient_ray_non_scale.py ├── policy_gradient.py ├── policy_gradient_gpu.py ├── running_state.py └── torch.py ├── envs ├── __init__.py ├── bandit.py ├── mdp.py ├── mujoco │ ├── __init__.py │ ├── ant.py │ ├── half_cheetah.py │ ├── hopper.py │ ├── humanoid.py │ └── walker2d.py ├── navigation.py ├── normalized_env.py ├── subproc_vec_env.py └── utils.py ├── policy_distillation.py ├── pretrain.py ├── pretrained_models ├── 2DNavigation-v1_0.pkl ├── 2DNavigation-v1_0_pretrain.pth.tar ├── 2DNavigation-v1_1.pkl ├── 2DNavigation-v1_10.pkl ├── 2DNavigation-v1_10_pretrain.pth.tar ├── 2DNavigation-v1_11.pkl ├── 2DNavigation-v1_11_pretrain.pth.tar ├── 2DNavigation-v1_12.pkl ├── 2DNavigation-v1_12_pretrain.pth.tar ├── 2DNavigation-v1_13.pkl ├── 2DNavigation-v1_13_pretrain.pth.tar ├── 2DNavigation-v1_14.pkl ├── 2DNavigation-v1_14_pretrain.pth.tar ├── 2DNavigation-v1_15.pkl ├── 2DNavigation-v1_15_pretrain.pth.tar ├── 2DNavigation-v1_16.pkl ├── 2DNavigation-v1_16_pretrain.pth.tar ├── 2DNavigation-v1_17.pkl ├── 2DNavigation-v1_17_pretrain.pth.tar ├── 2DNavigation-v1_18.pkl ├── 2DNavigation-v1_18_pretrain.pth.tar ├── 2DNavigation-v1_19.pkl ├── 2DNavigation-v1_19_pretrain.pth.tar ├── 2DNavigation-v1_1_pretrain.pth.tar ├── 2DNavigation-v1_2.pkl ├── 2DNavigation-v1_20.pkl ├── 2DNavigation-v1_20_pretrain.pth.tar ├── 2DNavigation-v1_21.pkl ├── 2DNavigation-v1_21_pretrain.pth.tar ├── 2DNavigation-v1_22.pkl ├── 2DNavigation-v1_22_pretrain.pth.tar ├── 2DNavigation-v1_23.pkl ├── 2DNavigation-v1_23_pretrain.pth.tar ├── 2DNavigation-v1_24.pkl ├── 2DNavigation-v1_24_pretrain.pth.tar ├── 2DNavigation-v1_25.pkl ├── 2DNavigation-v1_25_pretrain.pth.tar ├── 2DNavigation-v1_26.pkl ├── 2DNavigation-v1_26_pretrain.pth.tar ├── 2DNavigation-v1_27.pkl ├── 2DNavigation-v1_27_pretrain.pth.tar ├── 2DNavigation-v1_28.pkl ├── 2DNavigation-v1_28_pretrain.pth.tar ├── 2DNavigation-v1_29.pkl ├── 2DNavigation-v1_29_pretrain.pth.tar ├── 2DNavigation-v1_2_pretrain.pth.tar ├── 2DNavigation-v1_3.pkl ├── 2DNavigation-v1_30.pkl ├── 2DNavigation-v1_30_pretrain.pth.tar ├── 2DNavigation-v1_31.pkl ├── 2DNavigation-v1_31_pretrain.pth.tar ├── 2DNavigation-v1_32.pkl ├── 2DNavigation-v1_32_pretrain.pth.tar ├── 2DNavigation-v1_33.pkl ├── 2DNavigation-v1_33_pretrain.pth.tar ├── 2DNavigation-v1_34.pkl ├── 2DNavigation-v1_34_pretrain.pth.tar ├── 2DNavigation-v1_35.pkl ├── 2DNavigation-v1_35_pretrain.pth.tar ├── 2DNavigation-v1_36.pkl ├── 2DNavigation-v1_36_pretrain.pth.tar ├── 2DNavigation-v1_37.pkl ├── 2DNavigation-v1_37_pretrain.pth.tar ├── 2DNavigation-v1_38.pkl ├── 2DNavigation-v1_38_pretrain.pth.tar ├── 2DNavigation-v1_39.pkl ├── 2DNavigation-v1_39_pretrain.pth.tar ├── 2DNavigation-v1_3_pretrain.pth.tar ├── 2DNavigation-v1_4.pkl ├── 2DNavigation-v1_40.pkl ├── 2DNavigation-v1_40_pretrain.pth.tar ├── 2DNavigation-v1_41.pkl ├── 2DNavigation-v1_41_pretrain.pth.tar ├── 2DNavigation-v1_42.pkl ├── 2DNavigation-v1_42_pretrain.pth.tar ├── 2DNavigation-v1_43.pkl ├── 2DNavigation-v1_43_pretrain.pth.tar ├── 2DNavigation-v1_44.pkl ├── 2DNavigation-v1_44_pretrain.pth.tar ├── 2DNavigation-v1_45.pkl ├── 2DNavigation-v1_45_pretrain.pth.tar ├── 2DNavigation-v1_46.pkl ├── 2DNavigation-v1_46_pretrain.pth.tar ├── 2DNavigation-v1_47.pkl ├── 2DNavigation-v1_47_pretrain.pth.tar ├── 2DNavigation-v1_48.pkl ├── 2DNavigation-v1_48_pretrain.pth.tar ├── 2DNavigation-v1_49.pkl ├── 2DNavigation-v1_49_pretrain.pth.tar ├── 2DNavigation-v1_4_pretrain.pth.tar ├── 2DNavigation-v1_5.pkl ├── 2DNavigation-v1_5_pretrain.pth.tar ├── 2DNavigation-v1_6.pkl ├── 2DNavigation-v1_6_pretrain.pth.tar ├── 2DNavigation-v1_7.pkl ├── 2DNavigation-v1_7_pretrain.pth.tar ├── 2DNavigation-v1_8.pkl ├── 2DNavigation-v1_8_pretrain.pth.tar ├── 2DNavigation-v1_9.pkl ├── 2DNavigation-v1_9_pretrain.pth.tar ├── HalfCheetah-v2_pretrain.pth.tar ├── Hopper-v2_0.pkl ├── Hopper-v2_0_pretrain.pth.tar ├── Walker2d-v2.pkl └── Walker2d-v2_pretrain.pth.tar ├── student.py ├── teacher.py ├── trpo.py ├── utils ├── replay_memory.py ├── torch.py └── utils.py └── utils2 ├── math.py ├── replay_memory.py └── torch.py /core/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/agent.py -------------------------------------------------------------------------------- /core/agent_noniid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/agent_noniid.py -------------------------------------------------------------------------------- /core/agent_ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/agent_ray.py -------------------------------------------------------------------------------- /core/agent_ray_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/agent_ray_gpu.py -------------------------------------------------------------------------------- /core/agent_ray_pd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/agent_ray_pd.py -------------------------------------------------------------------------------- /core/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/common.py -------------------------------------------------------------------------------- /core/common_ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/common_ray.py -------------------------------------------------------------------------------- /core/common_ray_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/common_ray_gpu.py -------------------------------------------------------------------------------- /core/common_ray_navi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/common_ray_navi.py -------------------------------------------------------------------------------- /core/log_determinant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/log_determinant.py -------------------------------------------------------------------------------- /core/log_determinant_hessian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/log_determinant_hessian.py -------------------------------------------------------------------------------- /core/log_determinant_hessian_ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/log_determinant_hessian_ray.py -------------------------------------------------------------------------------- /core/log_determinant_ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/log_determinant_ray.py -------------------------------------------------------------------------------- /core/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/models.py -------------------------------------------------------------------------------- /core/natural_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/natural_gradient.py -------------------------------------------------------------------------------- /core/natural_gradient_ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/natural_gradient_ray.py -------------------------------------------------------------------------------- /core/natural_gradient_ray_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/natural_gradient_ray_gpu.py -------------------------------------------------------------------------------- /core/natural_gradient_ray_non_scale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/natural_gradient_ray_non_scale.py -------------------------------------------------------------------------------- /core/policy_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/policy_gradient.py -------------------------------------------------------------------------------- /core/policy_gradient_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/policy_gradient_gpu.py -------------------------------------------------------------------------------- /core/running_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/running_state.py -------------------------------------------------------------------------------- /core/torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/core/torch.py -------------------------------------------------------------------------------- /envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/__init__.py -------------------------------------------------------------------------------- /envs/bandit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/bandit.py -------------------------------------------------------------------------------- /envs/mdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/mdp.py -------------------------------------------------------------------------------- /envs/mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /envs/mujoco/ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/mujoco/ant.py -------------------------------------------------------------------------------- /envs/mujoco/half_cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/mujoco/half_cheetah.py -------------------------------------------------------------------------------- /envs/mujoco/hopper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/mujoco/hopper.py -------------------------------------------------------------------------------- /envs/mujoco/humanoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/mujoco/humanoid.py -------------------------------------------------------------------------------- /envs/mujoco/walker2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/mujoco/walker2d.py -------------------------------------------------------------------------------- /envs/navigation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/navigation.py -------------------------------------------------------------------------------- /envs/normalized_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/normalized_env.py -------------------------------------------------------------------------------- /envs/subproc_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/subproc_vec_env.py -------------------------------------------------------------------------------- /envs/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/envs/utils.py -------------------------------------------------------------------------------- /policy_distillation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/policy_distillation.py -------------------------------------------------------------------------------- /pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrain.py -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_0.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_0.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_0_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_0_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_1.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_10.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_10.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_10_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_10_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_11.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_11.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_11_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_11_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_12.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_12.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_12_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_12_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_13.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_13.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_13_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_13_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_14.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_14.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_14_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_14_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_15.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_15.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_15_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_15_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_16.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_16.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_16_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_16_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_17.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_17.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_17_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_17_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_18.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_18.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_18_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_18_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_19.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_19.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_19_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_19_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_1_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_1_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_2.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_20.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_20.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_20_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_20_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_21.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_21.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_21_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_21_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_22.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_22.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_22_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_22_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_23.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_23.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_23_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_23_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_24.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_24.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_24_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_24_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_25.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_25.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_25_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_25_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_26.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_26.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_26_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_26_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_27.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_27.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_27_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_27_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_28.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_28.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_28_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_28_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_29.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_29.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_29_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_29_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_2_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_2_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_3.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_3.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_30.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_30.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_30_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_30_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_31.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_31.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_31_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_31_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_32.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_32.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_32_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_32_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_33.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_33.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_33_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_33_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_34.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_34.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_34_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_34_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_35.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_35.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_35_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_35_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_36.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_36.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_36_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_36_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_37.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_37.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_37_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_37_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_38.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_38.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_38_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_38_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_39.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_39.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_39_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_39_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_3_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_3_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_4.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_4.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_40.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_40.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_40_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_40_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_41.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_41.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_41_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_41_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_42.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_42.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_42_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_42_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_43.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_43.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_43_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_43_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_44.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_44.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_44_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_44_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_45.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_45.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_45_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_45_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_46.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_46.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_46_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_46_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_47.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_47.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_47_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_47_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_48.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_48.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_48_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_48_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_49.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_49.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_49_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_49_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_4_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_4_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_5.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_5.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_5_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_5_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_6.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_6.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_6_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_6_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_7.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_7.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_7_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_7_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_8.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_8.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_8_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_8_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_9.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_9.pkl -------------------------------------------------------------------------------- /pretrained_models/2DNavigation-v1_9_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/2DNavigation-v1_9_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/HalfCheetah-v2_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/HalfCheetah-v2_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/Hopper-v2_0.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/Hopper-v2_0.pkl -------------------------------------------------------------------------------- /pretrained_models/Hopper-v2_0_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/Hopper-v2_0_pretrain.pth.tar -------------------------------------------------------------------------------- /pretrained_models/Walker2d-v2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/Walker2d-v2.pkl -------------------------------------------------------------------------------- /pretrained_models/Walker2d-v2_pretrain.pth.tar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/pretrained_models/Walker2d-v2_pretrain.pth.tar -------------------------------------------------------------------------------- /student.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/student.py -------------------------------------------------------------------------------- /teacher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/teacher.py -------------------------------------------------------------------------------- /trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/trpo.py -------------------------------------------------------------------------------- /utils/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/utils/replay_memory.py -------------------------------------------------------------------------------- /utils/torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/utils/torch.py -------------------------------------------------------------------------------- /utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/utils/utils.py -------------------------------------------------------------------------------- /utils2/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/utils2/math.py -------------------------------------------------------------------------------- /utils2/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/utils2/replay_memory.py -------------------------------------------------------------------------------- /utils2/torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Mee321/policy-distillation/HEAD/utils2/torch.py --------------------------------------------------------------------------------