issues
search
UoA-CARES
/
cares_reinforcement_learning
CARES Reinforcement Learning Package
10
stars
2
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
In the original MAPERTD3 algorithm, the parameter alpha is sent to memory, we do not utilize it, too.
#152
h-yamani
closed
5 months ago
1
Updated names of predicted and real rewards
#151
h-yamani
closed
5 months ago
1
Fall Clean
#150
beardyFace
closed
5 months ago
0
TQC
#149
beardyFace
closed
5 months ago
0
Plotter -p option
#148
beardyFace
closed
5 months ago
0
Training to Algorithm Configuration Refactor
#147
beardyFace
closed
5 months ago
0
REDQ
#146
beardyFace
closed
5 months ago
0
PALTD3
#145
beardyFace
closed
5 months ago
0
Memory Sample Consecutive
#144
beardyFace
closed
5 months ago
0
MAPERTD3
#143
beardyFace
closed
5 months ago
1
Update - checkpoint_frequency
#142
rainingx683
opened
6 months ago
1
Implement - save training state for pause and restart training
#141
rainingx683
opened
6 months ago
0
Sample into Algorithm
#140
beardyFace
closed
6 months ago
0
minor errors with weight mse fixed
#139
beardyFace
closed
6 months ago
0
LA3PTD3
#138
beardyFace
closed
5 months ago
1
Added LAPTD3
#137
beardyFace
closed
6 months ago
1
Docs/add examples directory
#136
retinfai
opened
6 months ago
0
Implement - REDQ
#135
beardyFace
closed
5 months ago
0
Feature/per rd td3
#134
beardyFace
closed
6 months ago
1
merged with main
#133
beardyFace
closed
6 months ago
0
Feature/agent update statistics
#132
qiaoting159753
closed
6 months ago
0
Add an extra argument in TrainingConfig for training the world model
#131
qiaoting159753
closed
6 months ago
0
DYNA adapt to the new memory buffer, which has a new sample and sample_consecutive function.
#130
qiaoting159753
closed
5 months ago
7
train reward and dynamic prediciton together
#129
qiaoting159753
closed
6 months ago
0
TypeError create memory
#128
qiaoting159753
closed
6 months ago
0
Fix a figure resize issue
#127
qiaoting159753
closed
6 months ago
0
batch size to 256
#126
beardyFace
closed
7 months ago
0
Algorithm/dueling td3
#125
beardyFace
closed
6 months ago
0
Feature/normalization for mbrl
#124
qiaoting159753
closed
7 months ago
0
Add number steps per train policy config
#123
retinfai
closed
7 months ago
0
Better Avoid using keywords as a variable's name. Type Error when calling create_memory().
#122
qiaoting159753
closed
6 months ago
0
Add autoformatting workflow
#121
retinfai
closed
7 months ago
0
Dev/mbrl
#120
qiaoting159753
closed
7 months ago
1
Extract memory into own config type
#119
retinfai
closed
5 months ago
0
Adjust time out for memory add
#118
retinfai
closed
7 months ago
0
memory buffer problem
#117
dvalenciar
closed
7 months ago
0
Algorithm/stc td3
#116
dvalenciar
closed
8 months ago
0
Modified record to append to existing data instead of overwriting it
#115
ManfredStoiber
closed
9 months ago
0
RL parser bool to int
#114
beardyFace
closed
10 months ago
0
Revert "Dev/update sac to the paper"
#113
beardyFace
closed
10 months ago
0
Dev/update sac to the paper
#112
qiaoting159753
closed
10 months ago
0
RLParse parseargs bool bug
#111
beardyFace
closed
10 months ago
0
linting from black
#110
beardyFace
closed
10 months ago
0
OpenCV creates QT issue
#109
emilysteiner71
closed
3 months ago
0
feat: make network factory dynamic
#108
retinfai
closed
11 months ago
0
Adding network/actor&critic path to the RLParser
#107
retinfai
opened
11 months ago
0
chore: remove training loops
#106
retinfai
closed
11 months ago
0
fix td3 to original
#105
dvalenciar
closed
11 months ago
0
Dev/nasa td3
#104
beardyFace
closed
11 months ago
0
Added noise decay into policy loop
#103
beardyFace
closed
11 months ago
0
Previous
Next