diff --git a/hyperparams/a2c.yml b/hyperparams/a2c.yml
index ba9416e85..04af6c6af 100644
--- a/hyperparams/a2c.yml
+++ b/hyperparams/a2c.yml
@@ -19,6 +19,12 @@ CartPole-v1:
   policy: 'MlpPolicy'
   ent_coef: 0.0
 
+seals/CartPole-v0:
+  n_envs: 8
+  n_timesteps: !!float 5e5
+  policy: 'MlpPolicy'
+  ent_coef: 0.0
+
 LunarLander-v2:
   n_envs: 8
   n_timesteps: !!float 2e5
@@ -35,6 +41,13 @@ MountainCar-v0:
   policy: 'MlpPolicy'
   ent_coef: .0
 
+seals/MountainCar-v0:
+  normalize: true
+  n_envs: 16
+  n_timesteps: !!float 1e6
+  policy: 'MlpPolicy'
+  ent_coef: .0
+
 Acrobot-v1:
   normalize: true
   n_envs: 16
@@ -170,19 +183,39 @@ HalfCheetah-v3: &mujoco-defaults
   n_timesteps: !!float 1e6
   policy: 'MlpPolicy'
 
+seals/HalfCheetah-v0:
+  <<: *mujoco-defaults
+
 Ant-v3:
   <<: *mujoco-defaults
 
+seals/Ant-v0:
+  <<: *mujoco-defaults
+
 Hopper-v3:
   <<: *mujoco-defaults
 
+seals/Hopper-v0:
+  <<: *mujoco-defaults
+
 Walker2d-v3:
   <<: *mujoco-defaults
 
+seals/Walker2d-v0:
+  <<: *mujoco-defaults
+
 Humanoid-v3:
   <<: *mujoco-defaults
   n_timesteps: !!float 2e6
 
+seals/Humanoid-v0:
+  <<: *mujoco-defaults
+  n_timesteps: !!float 2e6
+
 Swimmer-v3:
   <<: *mujoco-defaults
   gamma: 0.9999
+
+seals/Swimmer-v0:
+  <<: *mujoco-defaults
+  gamma: 0.9999
diff --git a/hyperparams/ars.yml b/hyperparams/ars.yml
index e58d4fa3c..eb89cc211 100644
--- a/hyperparams/ars.yml
+++ b/hyperparams/ars.yml
@@ -5,6 +5,12 @@ CartPole-v1:
   policy: 'LinearPolicy'
   n_delta: 2
 
+seals/CartPole-v0:
+  n_envs: 1
+  n_timesteps: !!float 5e4
+  policy: 'LinearPolicy'
+  n_delta: 2
+
 # Tuned
 Pendulum-v1: &pendulum-params
   n_envs: 1
@@ -41,6 +47,11 @@ MountainCar-v0:
   n_delta: 8
   n_timesteps: !!float 5e5
 
+seals/MountainCar-v0:
+  <<: *pendulum-params
+  n_delta: 8
+  n_timesteps: !!float 5e5
+
 # Tuned
 MountainCarContinuous-v0:
   <<: *pendulum-params
@@ -119,6 +130,17 @@ Swimmer-v3:
   alive_bonus_offset: 0
   # normalize: "dict(norm_obs=True, norm_reward=False)"
 
+seals/Swimmer-v0:
+  n_envs: 1
+  policy: 'LinearPolicy'
+  n_timesteps: !!float 2e6
+  learning_rate: !!float 0.02
+  delta_std: !!float 0.01
+  n_delta: 1
+  n_top: 1
+  alive_bonus_offset: 0
+  # normalize: "dict(norm_obs=True, norm_reward=False)"
+
 Hopper-v3:
   n_envs: 1
   policy: 'LinearPolicy'
@@ -130,6 +152,17 @@ Hopper-v3:
   alive_bonus_offset: -1
   normalize: "dict(norm_obs=True, norm_reward=False)"
 
+seals/Hopper-v0:
+  n_envs: 1
+  policy: 'LinearPolicy'
+  n_timesteps: !!float 7e6
+  learning_rate: !!float 0.01
+  delta_std: !!float 0.025
+  n_delta: 8
+  n_top: 4
+  alive_bonus_offset: -1
+  normalize: "dict(norm_obs=True, norm_reward=False)"
+
 HalfCheetah-v3:
   n_envs: 1
   policy: 'LinearPolicy'
@@ -141,6 +174,17 @@ HalfCheetah-v3:
   alive_bonus_offset: 0
   normalize: "dict(norm_obs=True, norm_reward=False)"
 
+seals/HalfCheetah-v0:
+  n_envs: 1
+  policy: 'LinearPolicy'
+  n_timesteps: !!float 1.25e7
+  learning_rate: !!float 0.02
+  delta_std: !!float 0.03
+  n_delta: 32
+  n_top: 4
+  alive_bonus_offset: 0
+  normalize: "dict(norm_obs=True, norm_reward=False)"
+
 Walker2d-v3:
   n_envs: 1
   policy: 'LinearPolicy'
@@ -152,6 +196,17 @@ Walker2d-v3:
   alive_bonus_offset: -1
   normalize: "dict(norm_obs=True, norm_reward=False)"
 
+seals/Walker2d-v0:
+  n_envs: 1
+  policy: 'LinearPolicy'
+  n_timesteps: !!float 7.5e7
+  learning_rate: !!float 0.03
+  delta_std: !!float 0.025
+  n_delta: 40
+  n_top: 30
+  alive_bonus_offset: -1
+  normalize: "dict(norm_obs=True, norm_reward=False)"
+
 Ant-v3:
   n_envs: 1
   policy: 'LinearPolicy'
@@ -163,6 +218,17 @@ Ant-v3:
   alive_bonus_offset: -1
   normalize: "dict(norm_obs=True, norm_reward=False)"
 
+seals/Ant-v0:
+  n_envs: 1
+  policy: 'LinearPolicy'
+  n_timesteps: !!float 7.5e7
+  learning_rate: !!float 0.015
+  delta_std: !!float 0.025
+  n_delta: 60
+  n_top: 20
+  alive_bonus_offset: -1
+  normalize: "dict(norm_obs=True, norm_reward=False)"
+
 
 Humanoid-v3:
   n_envs: 1
@@ -175,6 +241,17 @@ Humanoid-v3:
   alive_bonus_offset: -5
   normalize: "dict(norm_obs=True, norm_reward=False)"
 
+seals/Humanoid-v0:
+  n_envs: 1
+  policy: 'LinearPolicy'
+  n_timesteps: !!float 2.5e8
+  learning_rate: 0.02
+  delta_std: 0.0075
+  n_delta: 256
+  n_top: 256
+  alive_bonus_offset: -5
+  normalize: "dict(norm_obs=True, norm_reward=False)"
+
 # Almost tuned
 BipedalWalker-v3:
   n_envs: 1
diff --git a/hyperparams/ddpg.yml b/hyperparams/ddpg.yml
index 14a53cfca..996cee226 100644
--- a/hyperparams/ddpg.yml
+++ b/hyperparams/ddpg.yml
@@ -131,21 +131,43 @@ HalfCheetah-v3: &mujoco-defaults
   noise_type: 'normal'
   noise_std: 0.1
 
+seals/HalfCheetah-v0:
+  <<: *mujoco-defaults
+
 Ant-v3:
   <<: *mujoco-defaults
 
+seals/Ant-v0:
+  <<: *mujoco-defaults
+
 Hopper-v3:
   <<: *mujoco-defaults
 
+seals/Hopper-v0:
+  <<: *mujoco-defaults
+
 Walker2d-v3:
   <<: *mujoco-defaults
 
+seals/Walker2d-v0:
+  <<: *mujoco-defaults
+
 Humanoid-v3:
   <<: *mujoco-defaults
   n_timesteps: !!float 2e6
 
+seals/Humanoid-v0:
+  <<: *mujoco-defaults
+  n_timesteps: !!float 2e6
+
 Swimmer-v3:
   <<: *mujoco-defaults
   gamma: 0.9999
   train_freq: 1
   gradient_steps: 1
+
+seals/Swimmer-v0:
+  <<: *mujoco-defaults
+  gamma: 0.9999
+  train_freq: 1
+  gradient_steps: 1
diff --git a/hyperparams/dqn.yml b/hyperparams/dqn.yml
index b91d6c474..5f63ac67b 100644
--- a/hyperparams/dqn.yml
+++ b/hyperparams/dqn.yml
@@ -33,6 +33,21 @@ CartPole-v1:
   exploration_final_eps: 0.04
   policy_kwargs: "dict(net_arch=[256, 256])"
 
+seals/CartPole-v0:
+  n_timesteps: !!float 5e4
+  policy: 'MlpPolicy'
+  learning_rate: !!float 2.3e-3
+  batch_size: 64
+  buffer_size: 100000
+  learning_starts: 1000
+  gamma: 0.99
+  target_update_interval: 10
+  train_freq: 256
+  gradient_steps: 128
+  exploration_fraction: 0.16
+  exploration_final_eps: 0.04
+  policy_kwargs: "dict(net_arch=[256, 256])"
+
 # Tuned
 MountainCar-v0:
   n_timesteps: !!float 1.2e5
@@ -49,6 +64,21 @@ MountainCar-v0:
   exploration_final_eps: 0.07
   policy_kwargs: "dict(net_arch=[256, 256])"
 
+seals/MountainCar-v0:
+  n_timesteps: !!float 1.2e5
+  policy: 'MlpPolicy'
+  learning_rate: !!float 4e-3
+  batch_size: 128
+  buffer_size: 10000
+  learning_starts: 1000
+  gamma: 0.98
+  target_update_interval: 600
+  train_freq: 16
+  gradient_steps: 8
+  exploration_fraction: 0.2
+  exploration_final_eps: 0.07
+  policy_kwargs: "dict(net_arch=[256, 256])"
+
 # Tuned
 LunarLander-v2:
   n_timesteps: !!float 1e5
diff --git a/hyperparams/ppo.yml b/hyperparams/ppo.yml
index 10909fbe8..1d0d3b5d2 100644
--- a/hyperparams/ppo.yml
+++ b/hyperparams/ppo.yml
@@ -42,6 +42,23 @@ CartPole-v1:
   learning_rate: lin_0.001
   clip_range: lin_0.2
 
+# Tuned
+seals/CartPole-v0:
+  n_envs: 8
+  n_timesteps: !!float 1e5
+  policy: 'MlpPolicy'
+  batch_size: 256
+  clip_range: 0.4
+  ent_coef: 0.008508727919228772
+  gae_lambda: 0.9
+  gamma: 0.9999
+  learning_rate: 0.0012403278189645594
+  max_grad_norm: 0.8
+  n_epochs: 10
+  n_steps: 512
+  policy_kwargs: dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  vf_coef: 0.489343896591493
+
 MountainCar-v0:
   normalize: true
   n_envs: 16
@@ -53,6 +70,24 @@ MountainCar-v0:
   n_epochs: 4
   ent_coef: 0.0
 
+# Tuned
+seals/MountainCar-v0:
+  normalize: true
+  n_envs: 16
+  n_timesteps: !!float 1e6
+  policy: 'MlpPolicy'
+  batch_size: 512
+  clip_range: 0.2
+  ent_coef: 6.4940755116195606e-06
+  gae_lambda: 0.98
+  gamma: 0.99
+  learning_rate: 0.0004476103728105138
+  max_grad_norm: 1
+  n_epochs: 20
+  n_steps: 256
+  policy_kwargs: dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  vf_coef: 0.25988158989488963
+
 # Tuned
 MountainCarContinuous-v0:
   normalize: true
@@ -360,6 +395,21 @@ Ant-v3: &mujoco-defaults
   n_timesteps: !!float 1e6
   policy: 'MlpPolicy'
 
+# Tuned
+seals/Ant-v0:
+  <<: *mujoco-defaults
+  batch_size: 16
+  clip_range: 0.3
+  ent_coef: 3.1441389214159857e-06
+  gae_lambda: 0.8
+  gamma: 0.995
+  learning_rate: 0.00017959211641976886
+  max_grad_norm: 0.9
+  n_epochs: 10
+  n_steps: 2048
+  policy_kwargs: dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  vf_coef: 0.4351450387648799
+
 # Hopper-v3:
 #   <<: *mujoco-defaults
 #
@@ -374,6 +424,21 @@ Swimmer-v3:
   <<: *mujoco-defaults
   gamma: 0.9999
 
+# Tuned
+seals/Swimmer-v0:
+  <<: *mujoco-defaults
+  batch_size: 8
+  clip_range: 0.1
+  ent_coef: 5.167107294612664e-08
+  gae_lambda: 0.95
+  gamma: 0.999
+  learning_rate: 0.0001214437022727675
+  max_grad_norm: 2
+  n_epochs: 20
+  n_steps: 2048
+  policy_kwargs: dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  vf_coef: 0.6162112311062333
+
 # Tuned
 # 10 mujoco envs
 
@@ -399,6 +464,24 @@ HalfCheetah-v3:
                     net_arch=[dict(pi=[256, 256], vf=[256, 256])]
                   )"
 
+# Tuned
+seals/HalfCheetah-v0:
+  normalize: true
+  n_envs: 1
+  policy: 'MlpPolicy'
+  n_timesteps: !!float 1e6
+  batch_size: 64
+  clip_range: 0.1
+  ent_coef: 3.794797423594763e-06
+  gae_lambda: 0.95
+  gamma: 0.95
+  learning_rate: 0.0003286871805949382
+  max_grad_norm: 0.8
+  n_epochs: 5
+  n_steps: 512
+  policy_kwargs: dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  vf_coef: 0.11483689492120866
+
 # Ant-v3:
 #   normalize: true
 #   n_envs: 1
@@ -437,6 +520,24 @@ Hopper-v3:
                     net_arch=[dict(pi=[256, 256], vf=[256, 256])]
                   )"
 
+# Tuned
+seals/Hopper-v0:
+  normalize: true
+  n_envs: 1
+  policy: 'MlpPolicy'
+  n_timesteps: !!float 1e6
+  batch_size: 512
+  clip_range: 0.1
+  ent_coef: 0.0010159833764878474
+  gae_lambda: 0.98
+  gamma: 0.995
+  learning_rate: 0.0003904770450788824
+  max_grad_norm: 0.9
+  n_epochs: 20
+  n_steps: 2048
+  policy_kwargs: dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  vf_coef: 0.20315938606555833
+
 HumanoidStandup-v3:
   normalize: true
   n_envs: 1
@@ -481,6 +582,25 @@ Humanoid-v3:
                     net_arch=[dict(pi=[256, 256], vf=[256, 256])]
                   )"
 
+# Tuned
+seals/Humanoid-v0:
+  normalize: true
+  n_envs: 1
+  policy: 'MlpPolicy'
+  n_timesteps: !!float 1e7
+  batch_size: 256
+  clip_range: 0.2
+  ent_coef: 2.0745206045994986e-05
+  gae_lambda: 0.92
+  gamma: 0.999
+  learning_rate: 2.0309225666232827e-05
+  max_grad_norm: 0.5
+  n_epochs: 20
+  n_steps: 2048
+  policy_kwargs: dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[256, 256], vf=[256,
+    256])])
+  vf_coef: 0.819262464558427
+
 InvertedDoublePendulum-v3:
   normalize: true
   n_envs: 1
@@ -544,3 +664,22 @@ Walker2d-v3:
   gae_lambda: 0.95
   max_grad_norm: 1
   vf_coef: 0.871923
+
+# Tuned
+seals/Walker2d-v0:
+  normalize: true
+  n_envs: 1
+  policy: 'MlpPolicy'
+  n_timesteps: !!float 1e6
+  batch_size: 8
+  clip_range: 0.4
+  ent_coef: 0.00013057334805552262
+  gae_lambda: 0.92
+  gamma: 0.98
+  learning_rate: 3.791707778339674e-05
+  max_grad_norm: 0.6
+  n_epochs: 5
+  n_steps: 2048
+  policy_kwargs: dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[256, 256], vf=[256,
+    256])])
+  vf_coef: 0.6167177795726859
diff --git a/hyperparams/qrdqn.yml b/hyperparams/qrdqn.yml
index d1da3e5fd..31275d9be 100644
--- a/hyperparams/qrdqn.yml
+++ b/hyperparams/qrdqn.yml
@@ -25,6 +25,21 @@ CartPole-v1:
   exploration_final_eps: 0.04
   policy_kwargs: "dict(net_arch=[256, 256], n_quantiles=10)"
 
+seals/CartPole-v0:
+  n_timesteps: !!float 5e4
+  policy: 'MlpPolicy'
+  learning_rate: !!float 2.3e-3
+  batch_size: 64
+  buffer_size: 100000
+  learning_starts: 1000
+  gamma: 0.99
+  target_update_interval: 10
+  train_freq: 256
+  gradient_steps: 128
+  exploration_fraction: 0.16
+  exploration_final_eps: 0.04
+  policy_kwargs: "dict(net_arch=[256, 256], n_quantiles=10)"
+
 # Tuned
 MountainCar-v0:
   n_timesteps: !!float 1.2e5
@@ -41,6 +56,21 @@ MountainCar-v0:
   exploration_final_eps: 0.07
   policy_kwargs: "dict(net_arch=[256, 256], n_quantiles=25)"
 
+seals/MountainCar-v0:
+  n_timesteps: !!float 1.2e5
+  policy: 'MlpPolicy'
+  learning_rate: !!float 4e-3
+  batch_size: 128
+  buffer_size: 10000
+  learning_starts: 1000
+  gamma: 0.98
+  target_update_interval: 600
+  train_freq: 16
+  gradient_steps: 8
+  exploration_fraction: 0.2
+  exploration_final_eps: 0.07
+  policy_kwargs: "dict(net_arch=[256, 256], n_quantiles=25)"
+
 # Tuned
 LunarLander-v2:
   n_timesteps: !!float 1e5
diff --git a/hyperparams/sac.yml b/hyperparams/sac.yml
index 9d41262e4..d49a29435 100644
--- a/hyperparams/sac.yml
+++ b/hyperparams/sac.yml
@@ -194,23 +194,96 @@ HalfCheetah-v3: &mujoco-defaults
   policy: 'MlpPolicy'
   learning_starts: 10000
 
+# Tuned
+seals/HalfCheetah-v0:
+  <<: *mujoco-defaults
+  batch_size: 2048
+  buffer_size: 100000
+  gamma: 0.95
+  learning_rate: 0.000884624878315995
+  learning_starts: 10000
+  policy_kwargs: dict(net_arch=[64, 64], log_std_init=-0.6932709443503001)
+  tau: 0.01
+  train_freq: 64
+
 Ant-v3:
   <<: *mujoco-defaults
 
+# Tuned
+seals/Ant-v0:
+  <<: *mujoco-defaults
+  batch_size: 512
+  buffer_size: 1000000
+  gamma: 0.98
+  learning_rate: 0.0018514039303149058
+  learning_starts: 1000
+  policy_kwargs: dict(net_arch=[256, 256], log_std_init=-2.2692589009754176)
+  tau: 0.05
+  train_freq: 64
+
 Hopper-v3:
   <<: *mujoco-defaults
 
+# Tuned
+seals/Hopper-v0:
+  <<: *mujoco-defaults
+  batch_size: 128
+  buffer_size: 100000
+  gamma: 0.98
+  learning_rate: 0.001709807687567946
+  learning_starts: 1000
+  policy_kwargs: dict(net_arch=[256, 256], log_std_init=-1.6829391077276037)
+  tau: 0.08
+  train_freq: 32
+
 Walker2d-v3:
   <<: *mujoco-defaults
 
+# Tuned
+seals/Walker2d-v0:
+  <<: *mujoco-defaults
+  batch_size: 128
+  buffer_size: 100000
+  gamma: 0.99
+  learning_rate: 0.0005845844772048097
+  learning_starts: 1000
+  policy_kwargs: dict(net_arch=[400, 300], log_std_init=0.1955317469998743)
+  tau: 0.02
+  train_freq: 1
+
 Humanoid-v3:
   <<: *mujoco-defaults
   n_timesteps: !!float 2e6
 
+# Tuned
+seals/Humanoid-v0:
+  <<: *mujoco-defaults
+  n_timesteps: !!float 2e6
+  batch_size: 64
+  buffer_size: 100000
+  gamma: 0.98
+  learning_rate: 4.426351861707874e-05
+  learning_starts: 20000
+  policy_kwargs: dict(net_arch=[400, 300], log_std_init=-0.1034412732183072)
+  tau: 0.08
+  train_freq: 8
+
 Swimmer-v3:
   <<: *mujoco-defaults
   gamma: 0.9999
 
+# Tuned
+seals/Swimmer-v0:
+  <<: *mujoco-defaults
+  batch_size: 128
+  buffer_size: 100000
+  gamma: 0.995
+  learning_rate: 0.00039981805535514633
+  learning_starts: 1000
+  policy_kwargs: dict(net_arch=[400, 300], log_std_init=-2.689958330139309)
+  tau: 0.01
+  train_freq: 256
+
 # === HER Robotics GoalEnvs ===
 
 FetchReach-v1:
diff --git a/hyperparams/td3.yml b/hyperparams/td3.yml
index 9b941516b..c29d49199 100644
--- a/hyperparams/td3.yml
+++ b/hyperparams/td3.yml
@@ -133,9 +133,15 @@ HalfCheetah-v3: &mujoco-defaults
   noise_type: 'normal'
   noise_std: 0.1
 
+seals/HalfCheetah-v0:
+  <<: *mujoco-defaults
+
 Ant-v3:
   <<: *mujoco-defaults
 
+seals/Ant-v0:
+  <<: *mujoco-defaults
+
 Hopper-v3:
   <<: *mujoco-defaults
   # SAC Hyperparams
@@ -144,9 +150,20 @@ Hopper-v3:
   learning_rate: !!float 3e-4
   batch_size: 256
 
+seals/Hopper-v0:
+  <<: *mujoco-defaults
+  # SAC Hyperparams
+  train_freq: 1
+  gradient_steps: 1
+  learning_rate: !!float 3e-4
+  batch_size: 256
+
 Walker2d-v3:
   <<: *mujoco-defaults
 
+seals/Walker2d-v0:
+  <<: *mujoco-defaults
+
 Humanoid-v3:
   <<: *mujoco-defaults
   n_timesteps: !!float 2e6
@@ -156,9 +173,24 @@ Humanoid-v3:
   learning_rate: !!float 3e-4
   batch_size: 256
 
+seals/Humanoid-v0:
+  <<: *mujoco-defaults
+  n_timesteps: !!float 2e6
+  # SAC Hyperparams
+  train_freq: 1
+  gradient_steps: 1
+  learning_rate: !!float 3e-4
+  batch_size: 256
+
 # Tuned
 Swimmer-v3:
   <<: *mujoco-defaults
   gamma: 0.9999
   train_freq: 1
   gradient_steps: 1
+
+seals/Swimmer-v0:
+  <<: *mujoco-defaults
+  gamma: 0.9999
+  train_freq: 1
+  gradient_steps: 1
diff --git a/hyperparams/tqc.yml b/hyperparams/tqc.yml
index d26289bef..1dd42fc88 100644
--- a/hyperparams/tqc.yml
+++ b/hyperparams/tqc.yml
@@ -145,24 +145,45 @@ HalfCheetah-v3: &mujoco-defaults
   policy: 'MlpPolicy'
   learning_starts: 10000
 
+seals/HalfCheetah-v0:
+  <<: *mujoco-defaults
+
 Ant-v3:
   <<: *mujoco-defaults
 
+seals/Ant-v0:
+  <<: *mujoco-defaults
+
 Hopper-v3:
   <<: *mujoco-defaults
   top_quantiles_to_drop_per_net: 5
 
+seals/Hopper-v0:
+  <<: *mujoco-defaults
+  top_quantiles_to_drop_per_net: 5
+
 Walker2d-v3:
   <<: *mujoco-defaults
 
+seals/Walker2d-v0:
+  <<: *mujoco-defaults
+
 Humanoid-v3:
   <<: *mujoco-defaults
   n_timesteps: !!float 2e6
 
+seals/Humanoid-v0:
+  <<: *mujoco-defaults
+  n_timesteps: !!float 2e6
+
 Swimmer-v3:
   <<: *mujoco-defaults
   gamma: 0.9999
 
+seals/Swimmer-v0:
+  <<: *mujoco-defaults
+  gamma: 0.9999
+
 # === HER Robotics GoalEnvs ===
 FetchReach-v1:
   env_wrapper: sb3_contrib.common.wrappers.TimeFeatureWrapper
diff --git a/hyperparams/trpo.yml b/hyperparams/trpo.yml
index c78263338..01fbfccba 100644
--- a/hyperparams/trpo.yml
+++ b/hyperparams/trpo.yml
@@ -11,6 +11,18 @@ CartPole-v1:
   learning_rate: !!float 1e-3
   n_critic_updates: 20
 
+seals/CartPole-v0:
+  n_envs: 2
+  n_timesteps: !!float 1e5
+  policy: 'MlpPolicy'
+  n_steps: 512
+  batch_size: 512
+  cg_damping: !!float 1e-3
+  gae_lambda: 0.98
+  gamma: 0.99
+  learning_rate: !!float 1e-3
+  n_critic_updates: 20
+
 # Tuned
 Pendulum-v1:
   n_envs: 2
@@ -60,6 +72,14 @@ MountainCar-v0:
   n_steps: 1024
   n_critic_updates: 20
 
+seals/MountainCar-v0:
+  normalize: true
+  n_envs: 2
+  n_timesteps: !!float 1e5
+  policy: 'MlpPolicy'
+  n_steps: 1024
+  n_critic_updates: 20
+
 # Tuned
 MountainCarContinuous-v0:
   normalize: True
@@ -122,25 +142,49 @@ Ant-v3: &mujoco-defaults
   <<: *pybullet-defaults
   n_timesteps: !!float 1e6
 
+seals/Ant-v0:
+  <<: *mujoco-defaults
+
 # Tuned
 HalfCheetah-v3:
   <<: *mujoco-defaults
   target_kl: 0.04
+
+seals/HalfCheetah-v0:
+  <<: *mujoco-defaults
+  target_kl: 0.04
+
 # Tuned
 Hopper-v3:
   <<: *mujoco-defaults
+
+seals/Hopper-v0:
+  <<: *mujoco-defaults
+
 # Tuned
 Walker2d-v3:
   <<: *mujoco-defaults
 
+seals/Walker2d-v0:
+  <<: *mujoco-defaults
+
 Humanoid-v3:
   <<: *mujoco-defaults
   n_timesteps: !!float 2e6
+
+seals/Humanoid-v0:
+  <<: *mujoco-defaults
+  n_timesteps: !!float 2e6
+
 # Tuned
 Swimmer-v3:
   <<: *mujoco-defaults
   gamma: 0.9999
 
+seals/Swimmer-v0:
+  <<: *mujoco-defaults
+  gamma: 0.9999
+
 # Tuned
 BipedalWalker-v3:
   <<: *mujoco-defaults