Add ReBRAC configs and source

configs/offline/rebrac/antmaze/large_diverse_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.002
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.002
+critic_learning_rate: 0.00005
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: antmaze-large-diverse-v2
+eval_episodes: 100
+eval_every: 50
+eval_seed: 42
+gamma: 0.999
+group: rebrac-antmaze-large-diverse-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: true
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/antmaze/large_play_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.002
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.001
+critic_learning_rate: 0.00005
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: antmaze-large-play-v2
+eval_episodes: 100
+eval_every: 50
+eval_seed: 42
+gamma: 0.999
+group: rebrac-antmaze-large-play-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: true
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/antmaze/medium_diverse_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.001
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.0
+critic_learning_rate: 0.00005
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: antmaze-medium-diverse-v2
+eval_episodes: 100
+eval_every: 50
+eval_seed: 42
+gamma: 0.999
+group: rebrac-antmaze-medium-diverse-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: true
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/antmaze/medium_play_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.001
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.0005
+critic_learning_rate: 0.00005
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: antmaze-medium-play-v2
+eval_episodes: 100
+eval_every: 50
+eval_seed: 42
+gamma: 0.999
+group: rebrac-antmaze-medium-play-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: true
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/antmaze/umaze_diverse_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.003
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.001
+critic_learning_rate: 0.00005
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: antmaze-umaze-diverse-v2
+eval_episodes: 100
+eval_every: 50
+eval_seed: 42
+gamma: 0.999
+group: rebrac-antmaze-umaze-diverse-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: true
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/antmaze/umaze_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.003
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.002
+critic_learning_rate: 0.00005
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: antmaze-umaze-v2
+eval_episodes: 100
+eval_every: 50
+eval_seed: 42
+gamma: 0.999
+group: rebrac-antmaze-umaze-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: true
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/door/cloned_v1.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.01
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.1
+critic_learning_rate: 0.0003
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: door-cloned-v1
+eval_episodes: 10
+eval_every: 5
+eval_seed: 42
+gamma: 0.99
+group: rebrac-door-cloned-v1
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: false
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/door/expert_v1.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.05
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.01
+critic_learning_rate: 0.0003
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: door-expert-v1
+eval_episodes: 10
+eval_every: 5
+eval_seed: 42
+gamma: 0.99
+group: rebrac-door-expert-v1
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: false
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/door/human_v1.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.1
+actor_learning_rate: 0.0003
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 256
+critic_bc_coef: 0.1
+critic_learning_rate: 0.0003
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: door-human-v1
+eval_episodes: 10
+eval_every: 5
+eval_seed: 42
+gamma: 0.99
+group: rebrac-door-human-v1
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: false
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/halfcheetah/expert_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.01
+actor_learning_rate: 0.001
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 1024
+critic_bc_coef: 0.01
+critic_learning_rate: 0.001
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: halfcheetah-expert-v2
+eval_episodes: 10
+eval_every: 5
+eval_seed: 42
+gamma: 0.99
+group: rebrac-halfcheetah-expert-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: false
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/halfcheetah/full_replay_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.001
+actor_learning_rate: 0.001
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 1024
+critic_bc_coef: 0.1
+critic_learning_rate: 0.001
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: halfcheetah-full-replay-v2
+eval_episodes: 10
+eval_every: 5
+eval_seed: 42
+gamma: 0.99
+group: rebrac-halfcheetah-full-replay-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: false
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/halfcheetah/medium_expert_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.01
+actor_learning_rate: 0.001
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 1024
+critic_bc_coef: 0.1
+critic_learning_rate: 0.001
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: halfcheetah-medium-expert-v2
+eval_episodes: 10
+eval_every: 5
+eval_seed: 42
+gamma: 0.99
+group: rebrac-halfcheetah-medium-expert-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: false
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0

configs/offline/rebrac/halfcheetah/medium_replay_v2.yaml

@@ -0,0 +1,28 @@
+actor_bc_coef: 0.01
+actor_learning_rate: 0.001
+actor_ln: false
+actor_n_hiddens: 3
+batch_size: 1024
+critic_bc_coef: 0.001
+critic_learning_rate: 0.001
+critic_ln: true
+critic_n_hiddens: 3
+dataset_name: halfcheetah-medium-replay-v2
+eval_episodes: 10
+eval_every: 5
+eval_seed: 42
+gamma: 0.99
+group: rebrac-halfcheetah-medium-replay-v2
+hidden_dim: 256
+name: rebrac
+noise_clip: 0.5
+normalize_q: true
+normalize_reward: false
+normalize_states: false
+num_epochs: 1000
+num_updates_on_epoch: 1000
+policy_freq: 2
+policy_noise: 0.2
+project: ReBRAC
+tau: 0.005
+train_seed: 0